diff --git a/data/datasets/R_Datasets.json b/data/datasets/R_Datasets.json index b4b7872f5..4f3528bb3 100644 --- a/data/datasets/R_Datasets.json +++ b/data/datasets/R_Datasets.json @@ -1,848 +1,4648 @@ { "categories": [ { "category_name": "Medicine", "subcategories": [ { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "A clinical trial to evaluate the efficacy of maintenance chemotherapy for acute myelogenous leukaemia was conducted by Embury et al. (1977) at Stanford University. After reaching a stage of remission through treatment by chemotherapy, patients were randomized into two groups. The first group received maintenance chemotherapy and the second group did not. The aim of the study was to see if maintenance chemotherapy increased the length of the remission. The data here formed a preliminary analysis which was conducted in October 1974.", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/bigcity.csv", "filename": "aml", "name": "Remission Times for Acute Myelogenous Leukaemia", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The data consist of measurements made on patients with malignant melanoma. Each patient had their tumour removed by surgery at the Department of Plastic Surgery, University Hospital of Odense, Denmark during the period 1962 to 1977. The surgery consisted of complete removal of the tumour together with about 2.5cm of the surrounding skin. Among the measurements taken were the thickness of the tumour and whether it was ulcerated or not. These are thought to be important prognostic variables in that patients with a thick and/or ulcerated tumour have an increased chance of death from melanoma. Patients were followed until the end of 1977. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/melanoma.csv", "filename": "melanoma", "name": " Survival from Malignant Melanoma ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The treatment strategy for a patient diagnosed with cancer of the prostate depend highly on whether the cancer has spread to the surrounding lymph nodes. It is common to operate on the patient to get samples from the nodes which can then be analysed under a microscope but clearly it would be preferable if an accurate assessment of nodal involvement could be made without surgery. \nFor a sample of 53 prostate cancer patients, a number of possible predictor variables were measured before surgery. The patients then had surgery to determine nodal involvement. It was required to see if nodal involvement could be accurately predicted from the predictor variables and which ones were most important. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/nodal.csv", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/nodal.csv", "filename": "nodal", "name": "Nodal Involvement in Prostate Cancer ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The remission data frame has 27 rows and 3 columns.", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/remission.csv", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/remission.csv", "filename": "remission", "name": "Cancer Remission and Cell Activity ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A portion of an experiment to determine the limit of blank/limit of detection in a biochemical assay. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/LoBD.csv", + "filename": "LoBD", + "name": " Cancer drug data use to provide an example of the use of the skew power distributions. ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data from a case-control study of (o)esophageal cancer in Ille-et-Vilaine, France. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/esoph.csv", + "filename": "esoph", + "name": "Smoking, Alcohol and (O)esophageal Cancer", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true } ], "subcategory_name": "Oncology" }, { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "Although all cases of AIDS in England and Wales must be reported to the Communicable Disease Surveillance Centre, there is often a considerable delay between the time of diagnosis and the time that it is reported. In estimating the prevalence of AIDS, account must be taken of the unknown number of cases which have been diagnosed but not reported. The data set here records the reported cases of AIDS diagnosed from July 1983 and until the end of 1992. The data are cross-classified by the date of diagnosis and the time delay in the reporting of the cases. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/aids.csv", "filename": "aids", "name": "Delay in AIDS Reporting in England and Wales", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "CD4 cells are carried in the blood as part of the human immune system. One of the effects of the HIV virus is that these cells die. The count of CD4 cells is used in determining the onset of full-blown AIDS in a patient. In this study of the effectiveness of a new anti-viral drug on HIV, 20 HIV-positive patients had their CD4 counts recorded and then were put on a course of treatment with this drug. After using the drug for one year, their CD4 counts were again recorded. The aim of the experiment was to show that patients taking the drug had increased CD4 counts which is not generally seen in HIV-positive patients.", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/cd4.csv", "filename": "CD4", "name": "CD4 Counts for HIV-Positive Patients", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true } ], "subcategory_name": "AIDS" }, { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "In 1961 Doll and Hill sent out a questionnaire to all men on the British Medical Register enquiring about their smoking habits. Almost 70% of such men replied. Death certificates were obtained for medical practitioners and causes of death were assigned on the basis of these certificates. The breslow data set contains the person-years of observations and deaths from coronary artery disease accumulated during the first ten years of the study. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/breslow.csv", "filename": "breslow", "name": "Smoking Deaths Among Doctors ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The co.transfer data frame has 7 rows and 2 columns. Seven smokers with chickenpox had their levels of carbon monoxide transfer measured on entry to hospital and then again after 1 week. The main question being whether one week of hospitalization has changed the carbon monoxide transfer factor. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/co.transfer.csv", "filename": "co_transfer", "name": "Carbon Monoxide Transfer ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A simple data set with only 6 observations. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/smoking.csv", + "filename": "smoking", + "name": "smoking", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true } ], "subcategory_name": "Smoking" }, { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "Howard Grimes from the Botany Department, North Carolina State University, conducted an experiment for biochemical analysis of intracellular storage and transport of calcium across plasma membrane. Cells were suspended in a solution of radioactive calcium for a certain length of time and then the amount of radioactive calcium that was absorbed by the cells was measured. The experiment was repeated independently with 9 different times of suspension each replicated 3 times. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/calcium.csv", "filename": "calcium", "name": "Calcium Uptake Data ", "number_format": 0, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The data are from an experiment which was designed to look for a relationship between a certain genetic characteristic and handedness. The 37 subjects were women who had a son with mental retardation due to inheriting a defective X-chromosome. For each such mother a genetic measurement of their DNA was made. Larger values of this measurement are known to be linked to the defective gene and it was hypothesized that larger values might also be linked to a progressive shift away from right-handednesss. Each woman also filled in a questionnaire regarding which hand they used for various tasks. From these questionnaires a measure of hand preference was found for each mother. The scale of this measure goes from 1, indicating someone who always favours their right hand, to 8, indicating someone who always favours their left hand. Between these two extremes are people who favour one hand for some tasks and the other for other tasks. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/claridge.csv", "filename": "claridge", "name": "Genetic Links to Left-handedness ", "number_format": 0, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The data consist of measurements of the length and breadth of the heads of pairs of adult brothers in 25 randomly sampled families. All measurements are expressed in millimetres. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/frets.csv", "filename": "frets", "name": "Head Dimensions in Brothers ", "number_format": 0, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The data gives the positions of the individual caveolae in a square region with sides of length 500 units. This grid was originally on a 2.65mum square of muscle fibre. The data are those points falling in the lower left hand quarter of the region used for the dataset caveolae.dat in the spatial package by B.D. Ripley (1994). ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/cav.csv", "filename": "cav", "name": "Position of Muscle Caveolae ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "79 urine specimens were analyzed in an effort to determine if certain physical characteristics of the urine might be related to the formation of calcium oxalate crystals. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/urine.csv", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/urine.csv", "filename": "urine", "name": "Urine Analysis Data ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Common" - }, - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Down's syndrome is a genetic disorder caused by an extra chromosome 21 or a part of chromosome 21 being translocated to another chromosome. The incidence of Down's syndrome is highly dependent on the mother's age and rises sharply after age 30. In the 1960's a large scale study of the effect of maternal age on the incidence of Down's syndrome was conducted at the British Columbia Health Surveillance Registry. These are the data which was collected in that study. \nMothers were classified by age. Most groups correspond to the age in years but the first group comprises all mothers with ages in the range 15-17 and the last is those with ages 46-49. No data for mothers over 50 or below 15 were collected. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/downs.bc.csv", - "filename": "downs_bc", - "name": " Incidence of Down's Syndrome in British Columbia\n", + "description": "The Blackmore data frame has 945 rows and 4 columns. Blackmore and Davis's data on exercise histories of 138 teenaged girls hospitalized for eating disorders and 98 control subjects. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Blackmore.csv", + "filename": "Blackmore", + "name": "Exercise Histories of Eating-Disordered and Control Subjects", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Genetics" - }, - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "neuro is a matrix containing times of observed firing of a neuron in windows of 250ms either side of the application of a stimulus to a human subject. Each row of the matrix is a replication of the experiment and there were a total of 469 replicates. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/neuro.csv", - "filename": "neuro", - "name": "Neurophysiological Point Process Data ", + "description": "The Davis data frame has 200 rows and 5 columns. The subjects were men and women engaged in regular exercise. There are some missing data. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Davis.csv", + "filename": "Davis", + "name": "Self-Reports of Height and Weight", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Neurology" - } - ] - }, - { - "category_name": "Nature", - "subcategories": [ - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "This data set is part of a long study into body temperature regulation in beavers. Four adult female beavers were live-trapped and had a temperature-sensitive radio transmitter surgically implanted. Readings were taken every 10 minutes. The location of the beaver was also recorded and her activity level was dichotomized by whether she was in the retreat or outside of it since high-intensity activities only occur outside of the retreat. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/beaver.csv", - "filename": "beaver", - "name": "Beaver Body Temperature Data ", + "description": "The DavisThin data frame has 191 rows and 7 columns. This is part of a larger dataset for a study of eating disorders. The seven variables in the data frame comprise a \"drive for thinness\" scale, to be formed by summing the items. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/DavisThin.csv", + "filename": "DavisThin", + "name": "Davis's Data on Drive for Thinness", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "144 adult (over 2kg in weight) cats used for experiments with the drug digitalis had their heart and body weight recorded. 47 of the cats were female and 97 were male. The catsM data frame consists of the data for the male cats. The full data are in dataset cats in package MASS.", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/catsM.csv", - "filename": "catsM", - "name": "Weight Data for Domestic Cats", + "description": "Subset of data on migraine treatments collected by Tammy Kostecki-Dillon. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/KosteckiDillon.csv", + "filename": "KosteckiDillon", + "name": "Treatment of Migraine Headaches", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Data on the cardiac oxygen consumption and left ventricular pressure were gathered on 7 domestic dogs.", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/dogs.csv", - "filename": "dogs", - "name": "Cardiac Data for Domestic Dogs ", - "number_format": 0, + "description": "These contrived repeated-measures data are taken from O'Brien and Kaiser (1985). The data are from an imaginary study in which 16 female and male subjects, who are divided into three treatments, are measured at a pretest, postest, and a follow-up session; during each session, they are measured at five occasions at intervals of one hour. The design, therefore, has two between-subject and two within-subject factors. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/OBrienKaiser.csv", + "filename": "OBrienKaiser", + "name": "O'Brien and Kaiser's Repeated-Measures Data", + "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Each row of the data frame represents a male duck who is a second generation cross of mallard and pintail ducks. For 11 such ducks a behavioural and plumage index were calculated. These were measured on scales devised for this experiment which was to examine whether there was any link between which species the ducks resembled physically and which they resembled in behaviour. The scale for the physical appearance ranged from 0 (identical in appearance to a mallard) to 20 (identical to a pintail). The behavioural traits of the ducks were on a scale from 0 to 15 with lower numbers indicating closer to mallard-like in behaviour. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/ducks.csv", - "filename": "ducks", - "name": "Behavioral and Plumage Characteristics of Hybrid Ducks ", - "number_format": 0, + "description": "The Robey data frame has 50 rows and 3 columns. The observations are developing nations around 1990. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Robey.csv", + "filename": "Robey", + "name": "Fertility and Contraception", + "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Sections were prepared from the brain of adult guinea pigs. Spontaneous currents that flowed into individual brain cells were then recorded and the peak amplitude of each current measured. The aim of the experiment was to see if the current flow was quantal in nature (i.e. that it is not a single burst but instead is built up of many smaller bursts of current). If the current was indeed quantal then it would be expected that the distribution of the current amplitude would be multimodal with modes at regular intervals. The modes would be expected to decrease in magnitude for higher current amplitudes. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/paulsen.csv", - "filename": "paulsen", - "name": " Neurotransmission in Guinea Pig Brains ", + "description": "Contrived data on weight loss and self esteem over three months, for three groups of individuals: Control, Diet and Diet + Exercise. The data constitute a double-multivariate design. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/WeightLoss.csv", + "filename": "WeightLoss", + "name": " Weight Loss Data ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The data form a 3x4 factorial experiment, the factors being three poisons and four treatments. Each combination of the two factors was used for four animals, the allocation to animals having been completely randomized.", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/poisons.csv", - "filename": "poisons", - "name": "Animal Survival Times", + "description": "Random subset of the 1991 Arizona Medicare data for patients hospitalized subsequent to undergoing a CABG (DRGs 106, 107) or PTCA (DRG 112) cardiovascular procedure. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/azcabgptca.csv", + "filename": "azcabgptca", + "name": "azcabgptca", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The data measured the survival percentages of batches of rats who were given varying doses of radiation. At each of 6 doses there were two or three replications of the experiment. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/survival.csv", - "filename": "survival", - "name": "Survival of Rats after Radiation Doses ", + "description": "The data set relates to the hospital length of stay for patients having a CABG or PTCA (typel) heart procedure. The data comes from the 1995 Arizona Medicare data for DRG (Diagnostic Related Group) 112. Other predictors include gender(1=female) and age75 (1-age 75+). Type is labeled as 1=emergency or urgent admission; 0= elective. Length of stay (los) ranges from 1 to 53 days. \n", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/azdrg112.csv", + "filename": "azdrg112", + "name": "azdrg112", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The data come from an aerial line transect survey of Southern Bluefin Tuna in the Great Australian Bight. An aircraft with two spotters on board flies randomly allocated line transects. Each school of tuna sighted is counted and its perpendicular distance from the transect measured. The survey was conducted in summer when tuna tend to stay on the surface. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/tuna.csv", - "filename": "tuna", - "name": " Tuna Sighting Data ", + "description": "Data come from the 1991 Arizona cardiovascular patient files. A subset of the fields was selected to model the differential length of stay for patients entering the hospital to receive one of two standard cardiovascular procedures: CABG and PTCA. CABG is the standard acronym for Coronary Artery Bypass Graft, where the flow of blood in a diseased or blocked coronary artery or vein has been grafted to bypass the diseased sections. PTCA, or Percutaneous Transluminal Coronary Angioplasty, is a method of placing a balloon in a blocked coronary artery to open it to blood flow. It is a much less severe method of treatment for those having coronary blockage, with a corresponding reduction in risk. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/azpro.csv", + "filename": "azpro", + "name": "azpro", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Animals" - }, - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Charles Darwin conducted an experiment to examine the superiority of cross-fertilized plants over self-fertilized plants. 15 pairs of plants were used. Each pair consisted of one cross-fertilized plant and one self-fertilized plant which germinated at the same time and grew in the same pot. The plants were measured at a fixed time after planting and the difference in heights between the cross- and self-fertilized plants are recorded in eighths of an inch.", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/darwin.csv", - "filename": "darwin", - "name": "Darwin's Plant Height Differences ", - "number_format": 0, + "description": "Data come from the 1991 Arizona cardiovascular patient files. A subset of the fields was selected to model the differential length of stay for patients entering the hospital to receive one of two standard cardiovascular procedures: CABG and PTCA. CABG is the standard acronym for Coronary Artery Bypass Graft, where the flow of blood in a diseased or blocked coronary artery or vein has been grafted to bypass the diseased sections. PTCA, or Percutaneous Transluminal Coronary Angioplasty, is a method of placing a balloon in a blocked coronary artery to open it to blood flow. It is a much less severe method of treatment for those having coronary blockage, with a corresponding reduction in risk. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/azprocedure.csv", + "filename": "azprocedure", + "name": "azprocedure", + "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The location of living bramble canes in a 9m square plot was recorded. We take 9m to be the unit of distance so that the plot can be thought of as a unit square. The bramble canes were also classified by their age. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/brambles.csv", - "filename": "brambles", - "name": "Spatial Location of Bramble Canes ", + "description": "From German health survey data for the year 1998 only. badhealth is saved as a data frame. Count models use numvisit as the response variable, 0 counts are included. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/badhealth.csv", + "filename": "badhealth", + "name": "badhealth", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The cane data frame has 180 rows and 5 columns. The data frame represents a randomized block design with 45 varieties of sugar-cane and 4 blocks.", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/cane.csv", - "filename": "cane", - "name": "Sugar-cane Disease Data ", + "description": "Data are from the Canadian National Cardiovascular Disease registry called, FASTRAK. years covered at 1996-1998. They have been grouped by covariate patterns from individual observations. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/fasttrakg.csv", + "filename": "fasttrakg", + "name": "fasttrakg", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The number of balsam-fir seedlings in each quadrant of a grid of 50 five foot square quadrants were counted. The grid consisted of 5 rows of 10 quadrants in each row. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/fir.csv", - "filename": "fir", - "name": "Counts of Balsam-fir Seedlings ", + "description": "grouped format of the lbw data. The observation level data come to us form Hosmer and Lemeshow (2000). Grouping is such that lowbw is the numerator, and cases the denominator of a binomial model, or cases may be an offset to the count variable, lowbw. Birthweights under 2500g classifies a low birthweight baby. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/lbwgrp.csv", + "filename": "lbwgrp", + "name": "lbwgrp", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Plants" - }, - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The data values are monthly averages of the daily stages (heights) of the Rio Negro at Manaus. Manaus is 18km upstream from the confluence of the Rio Negro with the Amazon but because of the tiny slope of the water surface and the lower courses of its flatland affluents, they may be regarded as a good approximation of the water level in the Amazon at the confluence. The data here cover 90 years from January 1903 until December 1992. \nThe Manaus gauge is tied in with an arbitrary bench mark of 100m set in the steps of the Municipal Prefecture; gauge readings are usually referred to sea level, on the basis of a mark on the steps leading to the Parish Church (Matriz), which is assumed to lie at an altitude of 35.874 m according to observations made many years ago under the direction of Samuel Pereira, an engineer in charge of the Manaus Sanitation Committee Whereas such an altitude cannot, by any means, be considered to be a precise datum point, observations have been provisionally referred to it. The measurements are in metres. \n", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/manaus.csv", - "filename": "manaus", - "name": "Average Heights of the Rio Negro river at Manaus", - "number_format": 0, + "description": "The US national Medicare inpatient hospital database is referred to as the Medpar data, which is prepared yearly from hospital filing records. Medpar files for each state are also prepared. The full Medpar data consists of 115 variables. The national Medpar has some 14 million records, with one record for each hospilitiztion. The data in the medpar file comes from 1991 Medicare files for the state of Arizona. The data are limited to only one diagnostic group (DRG 112). Patient data have been randomly selected from the original data. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/medpar.csv", + "filename": "medpar", + "name": "medpar", + "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Nitrofen is a herbicide that was used extensively for the control of broad-leaved and grass weeds in cereals and rice. Although it is relatively non-toxic to adult mammals, nitrofen is a significant tetragen and mutagen. It is also acutely toxic and reproductively toxic to cladoceran zooplankton. Nitrofen is no longer in commercial use in the U.S., having been the first pesticide to be withdrawn due to tetragenic effects. \nThe data here come from an experiment to measure the reproductive toxicity of nitrofen on a species of zooplankton (Ceriodaphnia dubia). 50 animals were randomized into batches of 10 and each batch was put in a solution with a measured concentration of nitrofen. Then the number of live offspring in each of the three broods to each animal was recorded. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/nitrofen.csv", - "filename": "nitrofen", - "name": "Toxicity of Nitrofen in Aquatic Systems ", + "description": "German health registry for the years 1984-1988. Health information for years prior to health reform. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/rwm.csv", + "filename": "rwm", + "name": "rwm", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Biweekly averages of the water salinity and river discharge in Pamlico Sound, North Carolina were recorded between the years 1972 and 1977. The data in this set consists only of those measurements in March, April and May. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/salinity.csv", - "filename": "salinity", - "name": "Water Salinity and River Discharge ", + "description": "German health registry for the year 1984. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/rwm1984.csv", + "filename": "rwm1984", + "name": "rwm1984", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Rivers" - }, - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The data are the pole positions from a paleomagnetic study of New Caledonian laterites. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/polar.csv", - "filename": "polar", - "name": "Pole Positions of New Caledonian Laterites ", + "description": "German health registry for the years 1984-1988. Health information for years immediately prior to health reform. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/rwm5yr.csv", + "filename": "rwm5yr", + "name": "rwm5yr", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Geology" - } - ] - }, - { - "category_name": "Statistics", - "subcategories": [ - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The measurements are the population (in 1000's) of 49 U.S. cities in 1920 and 1930. The 49 cities are a random sample taken from the 196 largest cities in 1920. The city data frame consists of the first 10 observations in bigcity.", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/bigcity.csv", - "filename": "bigcity", - "name": "Population of U.S. Cities", + "description": "Thirty patients were given an anesthetic agent maintained at a predetermined level (conc) for 15 minutes before making an incision. It was then noted whether the patient moved, i.e. jerked or twisted. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/anesthetic.csv", + "filename": "anesthetic", + "name": "Anesthetic Effectiveness", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", - "column_description_0": "index", - "column_description_1": "census year. ", - "column_description_2": "Population, in millions ", "comment_character": "#", "create_index_column": false, - "description": "The CanPop data frame has 16 rows and 2 columns. Decennial time-series of Canadian population, 1851–2001. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/CanPop.csv", - "filename": "CanPop", - "name": "Canadian Population Data", + "description": "The table shows, separately for males and females, the effect of pentazocine on post-operative pain profiles (average VAS scores), with (mbac and fbac) and without (mpl and fpl) preoperatively administered baclofen. Pain scores are recorded every 20 minutes, from 10 minutes to 170 minutes. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/gaba.csv", + "filename": "gaba", + "name": "Effect of pentazocine on post-operative pain (average VAS scores)", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Channing House is a retirement centre in Palo Alto, California. These data were collected between the opening of the house in 1964 until July 1, 1975. In that time 97 men and 365 women passed through the centre. For each of these, their age on entry and also on leaving or death was recorded. A large number of the observations were censored mainly due to the resident being alive on July 1, 1975 when the data was collected. Over the time of the study 130 women and 46 men died at Channing House. Differences between the survival of the sexes, taking age into account, was one of the primary concerns of this study. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/channing.csv", - "filename": "channing", - "name": " Channing House Data ", + "description": "The data set from Daedalus project. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/humanpower1.csv", + "filename": "humanpower", + "name": "Oxygen uptake versus mechanical power, for humans", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The measurements are the population (in 1000's) of 49 U.S. cities in 1920 and 1930. The 49 cities are a random sample taken from the 196 largest cities in 1920. The city data frame consists of the first 10 observations in bigcity. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/city.csv", - "filename": "city", - "name": "Population of U.S. Cities ", + "description": "Data in humanpower1 are from investigations (Bussolari 1987) designed to assess the feasibility of a proposed 119 kilometer human powered flight from the island of Crete – in the initial phase of the Daedalus project. Data are for five athletes – a female hockey player, a male amateur tri-athlete, a female amateur triathlete, a male wrestler and a male cyclist – who were selected from volunteers who were recruited through the news media, Data in humanpower2) are for four out of the 25 applicants who were selected for further testing, in the lead-up to the eventual selection of a pilot for the Daedalus project (Nadel and Bussolari 1988). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/humanpower2.csv", + "filename": "humanpower2", + "name": "Oxygen uptake versus mechanical power, for humans", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Demographics" - }, - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "In a study into the effect that warning signs have on speeding patterns, Cambridgeshire County Council considered 14 pairs of locations. The locations were paired to account for factors such as traffic volume and type of road. One site in each pair had a sign erected warning of the dangers of speeding and asking drivers to slow down. No action was taken at the second site. Three sets of measurements were taken at each site. Each set of measurements was nominally of the speeds of 100 cars but not all sites have exactly 100 measurements. These speed measurements were taken before the erection of the sign, shortly after the erection of the sign, and again after the sign had been in place for some time. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/amis.csv", - "filename": "amis", - "name": "Car Speeding and Warning Signs ", + "description": "Median blood pressure, as a fuction of salt intake, for each of 52 human populations. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/intersalt.csv", + "filename": "intersalt", + "name": "Blood pressure versus Salt; inter-population data", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Proschan (1963) reported on the times between failures of the air-conditioning equipment in 10 Boeing 720 aircraft. The aircondit data frame contains the intervals for the ninth aircraft while aircondit7 contains those for the seventh aircraft. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/aircondit.csv", - "filename": "aircondit", - "name": "Failures of Air-conditioning Equipment ", + "description": "Deaths in London from measles: 1629 – 1939, with gaps. ", + "download": "http://vincentarelbundock.github.io/Rdatasets/doc/DAAG/measles.csv", + "filename": "measles", + "name": "Deaths in London from measles", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Proschan (1963) reported on the times between failures of the air-conditioning equipment in 10 Boeing 720 aircraft. The aircondit data frame contains the intervals for the ninth aircraft while aircondit7 contains those for the seventh aircraft. \nBoth data frames have just one column. Note that the data have been sorted into increasing order. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/aircondit7.csv", - "filename": "aircondit7", - "name": "Failures of Air-conditioning Equipment ", + "description": "The mifem data frame has 1295 rows and 10 columns. This is the female subset of the 'monica' data frame ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/mifem.csv", + "filename": "mifem", + "name": "Mortality Outcomes for Females Suffering Myocardial Infarction", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The motor data frame has 94 rows and 4 columns. The rows are obtained by removing replicate values of time from the dataset mcycle. Two extra columns are added to allow for strata with a different residual variance in each stratum. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/motor.csv", - "filename": "motor", - "name": "Data from a Simulated Motorcycle Accident", + "description": "The monica data frame has 6357 rows and 12 columns. Note that mifem is the female subset of this data frame. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/monica.csv", + "filename": "monica", + "name": "WHO Monica Data", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true - } - ], - "subcategory_name": "Traffic" - }, - { - "datasets": [ + }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The excess return for the Acme Cleveland Corporation are recorded along with those for all stocks listed on the New York and American Stock Exchanges were recorded over a five year period. These excess returns are relative to the return on a risk-less investment such a U.S. Treasury bills. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/acme.csv", - "filename": "acme", - "name": "Monthly Excess Returns", + "description": "Deaths from \"flux\" or smallpox, measles, all causes, and ratios of the the first two categories to total deaths. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/poxetc.csv", + "filename": "poxetc", + "name": "Deaths from various causes, in London from 1629 till 1881, with gaps", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The data relate to the construction of 32 light water reactor (LWR) plants constructed in the U.S.A in the late 1960's and early 1970's. The data was collected with the aim of predicting the cost of construction of further LWR plants. 6 of the power plants had partial turnkey guarantees and it is possible that, for these plants, some manufacturers' subsidies may be hidden in the quoted capital costs. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/nuclear.csv", - "filename": "nuclear", - "name": " Nuclear Power Station Construction Data ", + "description": "Deaths from whooping cough, in London from 1740 to 1881. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/whoops.csv", + "filename": "whoops", + "name": "Deaths from whooping cough, in London", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "Each week that the market is open the Australian Wool Corporation set a floor price which determines their policy on intervention and is therefore a reflection of the overall price of wool for the week in question. Actual prices paid can vary considerably about the floor price. The series here is the log of the ratio between the price for fine grade wool and the floor price, each market week between July 1976 and Jun 1984. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/wool.csv", - "filename": "wool", - "name": " Australian Relative Wool Prices ", + "description": "This is a matched case-control study dating from before the availability of conditional logistic regression. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/infert.csv", + "filename": "infert", + "name": "Infertility after Spontaneous and Induced Abortion", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A regular time series giving the luteinizing hormone in blood samples at 10 mins intervals from a human female, 48 samples. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/lh.csv", + "filename": "lh", + "name": " Luteinizing Hormone in Blood Samples ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true } ], - "subcategory_name": "Economics" + "subcategory_name": "Common" }, { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The data are simulated successive observations from a process in equilibrium. The process is assumed to have specification limits (5.49, 5.79). ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/capability.csv", - "filename": "capability", - "name": "Simulated Manufacturing Process Data ", + "description": "Down's syndrome is a genetic disorder caused by an extra chromosome 21 or a part of chromosome 21 being translocated to another chromosome. The incidence of Down's syndrome is highly dependent on the mother's age and rises sharply after age 30. In the 1960's a large scale study of the effect of maternal age on the incidence of Down's syndrome was conducted at the British Columbia Health Surveillance Registry. These are the data which was collected in that study. \nMothers were classified by age. Most groups correspond to the age in years but the first group comprises all mothers with ages in the range 15-17 and the last is those with ages 46-49. No data for mothers over 50 or below 15 were collected. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/downs.bc.csv", + "filename": "downs_bc", + "name": " Incidence of Down's Syndrome in British Columbia\n", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "The cloth data frame has 32 rows and 2 columns. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/cloth.csv", - "filename": "cloth", - "name": "Number of Flaws in Cloth ", + "description": "The Burt data frame has 27 rows and 4 columns. The “data” were simply (and notoriously) manufactured. The same data are in the dataset “twins\" in the alr3 package, but with different labels. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Burt.csv", + "filename": "Burt", + "name": "Fraudulent Data on IQs of Twins Raised Apart", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, - "description": "This data frame gives the dates of 191 explosions in coal mines which resulted in 10 or more fatalities. The time span of the data is from March 15, 1851 until March 22 1962. ", - "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/coal.csv", - "filename": "coal", - "name": "Dates of Coal Mining Disasters ", + "description": "The data come to us from Hosmer and Lemeshow (2000). Called the low birth weight (lbw) data, the response is a binary variable, low, which indicates whether the birth weight of a baby is under 2500g (low=1), or over (low=0). ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/lbw.csv", + "filename": "lbw", + "name": "lbw", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true } ], - "subcategory_name": "Other" - } + "subcategory_name": "Genetics" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "neuro is a matrix containing times of observed firing of a neuron in windows of 250ms either side of the application of a stimulus to a human subject. Each row of the matrix is a replication of the experiment and there were a total of 469 replicates. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/neuro.csv", + "filename": "neuro", + "name": "Neurophysiological Point Process Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Friendly data frame has 30 rows and 2 columns. The data are from an experiment on subjects' ability to remember words based on the presentation format. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Friendly.csv", + "filename": "Friendly", + "name": "Format Effects on Recall", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The head.injury data frame has 3121 rows and 11 columns. The data were simulated according to a simple logistic regression model to match roughly the clinical characteristics of a sample of individuals who suffered minor head injuries. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/head.injury.csv", + "filename": "headinjury", + "name": "Minor Head Injury (Simulated) Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The headInjury data frame has 3121 rows and 11 columns. The data were simulated according to a simple logistic regression model to match roughly the clinical characteristics of a sample of individuals who suffered minor head injuries. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/headInjury.csv", + "filename": "headInjury", + "name": "Minor Head Injury (Simulated) Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Neurology" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Cowles data frame has 1421 rows and 4 columns. These data come from a study of the personality determinants of volunteering for psychological research. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Cowles.csv", + "filename": "Cowles", + "name": "Cowles and Davis's Data on Volunteering", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Ginzberg data frame has 82 rows and 6 columns. The data are for psychiatric patients hospitalized for depression. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Ginzberg.csv", + "filename": "Ginzberg", + "name": "Data on Depression", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data set illustrates analyis of a multifactor observational study, with response given by subject's score on a vocabulary test, and factors for age group, education level, natality status, gender and year of the survey. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/GSSvocab.csv", + "filename": "GSSvocab", + "name": " Data from the General Social Survey (GSS) from the National Opinion Research Center of the University of Chicago. ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Guyer data frame has 20 rows and 3 columns. The data are from an experiment in which four-person groups played a prisoner's dilemma game for 30 trails, each person making either a cooperative or competitive choice on each trial. Choices were made either anonymously or in public; groups were composed either of females or of males. The observations are 20 groups. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Guyer.csv", + "filename": "Guyer", + "name": "Anonymity and Cooperation", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Moore data frame has 45 rows and 4 columns. The data are for subjects in a social-psychological experiment, who were faced with manipulated disagreement from a partner of either of low or high status. The subjects could either conform to the partner's judgment or stick with their own judgment. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Moore.csv", + "filename": "Moore", + "name": "Status, Authoritarianism, and Conformity", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Wong data frame has 331 row and 7 columns. The observations are longitudinal data on recovery of IQ after comas of varying duration for 200 subjects.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Wong.csv", + "filename": "Wong", + "name": " Post-Coma Recovery of IQ ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Six tests were given to 112 individuals. The covariance matrix is given in this object. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/ability.cov.csv", + "filename": "abilityCov", + "name": "Ability and Intelligence Tests", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A correlation matrix of 24 psychological tests given to 145 seventh and eight-grade children in a Chicago suburb by Holzinger and Swineford. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/Harman74.cor.csv", + "filename": "Harman74cor", + "name": "Harman Example 7.4", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Psychology" + } + ] + }, + { + "category_name": "Nature", + "subcategories": [ + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data set is part of a long study into body temperature regulation in beavers. Four adult female beavers were live-trapped and had a temperature-sensitive radio transmitter surgically implanted. Readings were taken every 10 minutes. The location of the beaver was also recorded and her activity level was dichotomized by whether she was in the retreat or outside of it since high-intensity activities only occur outside of the retreat. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/beaver.csv", + "filename": "beaver", + "name": "Beaver Body Temperature Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "144 adult (over 2kg in weight) cats used for experiments with the drug digitalis had their heart and body weight recorded. 47 of the cats were female and 97 were male. The catsM data frame consists of the data for the male cats. The full data are in dataset cats in package MASS.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/catsM.csv", + "filename": "catsM", + "name": "Weight Data for Domestic Cats", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data on the cardiac oxygen consumption and left ventricular pressure were gathered on 7 domestic dogs.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/dogs.csv", + "filename": "dogs", + "name": "Cardiac Data for Domestic Dogs ", + "number_format": 0, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Each row of the data frame represents a male duck who is a second generation cross of mallard and pintail ducks. For 11 such ducks a behavioural and plumage index were calculated. These were measured on scales devised for this experiment which was to examine whether there was any link between which species the ducks resembled physically and which they resembled in behaviour. The scale for the physical appearance ranged from 0 (identical in appearance to a mallard) to 20 (identical to a pintail). The behavioural traits of the ducks were on a scale from 0 to 15 with lower numbers indicating closer to mallard-like in behaviour. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/ducks.csv", + "filename": "ducks", + "name": "Behavioral and Plumage Characteristics of Hybrid Ducks ", + "number_format": 0, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Sections were prepared from the brain of adult guinea pigs. Spontaneous currents that flowed into individual brain cells were then recorded and the peak amplitude of each current measured. The aim of the experiment was to see if the current flow was quantal in nature (i.e. that it is not a single burst but instead is built up of many smaller bursts of current). If the current was indeed quantal then it would be expected that the distribution of the current amplitude would be multimodal with modes at regular intervals. The modes would be expected to decrease in magnitude for higher current amplitudes. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/paulsen.csv", + "filename": "paulsen", + "name": " Neurotransmission in Guinea Pig Brains ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data form a 3x4 factorial experiment, the factors being three poisons and four treatments. Each combination of the two factors was used for four animals, the allocation to animals having been completely randomized.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/poisons.csv", + "filename": "poisons", + "name": "Animal Survival Times", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data measured the survival percentages of batches of rats who were given varying doses of radiation. At each of 6 doses there were two or three replications of the experiment. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/survival.csv", + "filename": "survival", + "name": "Survival of Rats after Radiation Doses ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data come from an aerial line transect survey of Southern Bluefin Tuna in the Great Australian Bight. An aircraft with two spotters on board flies randomly allocated line transects. Each school of tuna sighted is counted and its perpendicular distance from the transect measured. The survey was conducted in summer when tuna tend to stay on the surface. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/tuna.csv", + "filename": "tuna", + "name": " Tuna Sighting Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Wolf depredations of livestock on Minnesota farms, 1976-1998. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Depredations.csv", + "filename": "Depredations", + "name": " Minnesota Wolf Depredation Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This is a three-factor experiment with each factor at three levels, for a total of 27 runs. Samples of worsted yarn were with different levels of the three factors were given a cyclic load until the sample failed. The goal is to understand how cycles to failure depends on the factors. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Wool.csv", + "filename": "Wool", + "name": "Wool data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data set considers 6 binary attributes for 20 animals. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/animals.csv", + "filename": "animals", + "name": "Attributes of Animals", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The fishing data is adapted from Zuur, Hilbe and Ieno (2013) to determine whether the data appears to be generated from more than one generating mechanism. The data are originally adapted from Bailey et al. (2008) who were interested in how certain deep-sea fish populations were impacted when commercial fishing began in locations with deeper water than in previous years. Given that there are 147 sites that were researched, the model is of (1) the total number of fish counted per site (totabund); ( 2) on the mean water depth per site (meandepth); (3) adjusted by the area of the site (sweptarea); (4) the log of which is the model offset. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/fishing.csv", + "filename": "fishing", + "name": "fishing", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Squirrel data set (nuts) from Zuur, Hilbe, and Ieno (2013). As originally reported by Flaherty et al (2012), researchers recorded information about squirrel behavior and forest attributes across various plots in Scotland's Abernathy Forest. The study focused on the following variables. response cones number of cones stripped by red squirrels per plot predictor sntrees standardized number of trees per plot sheight standardized mean tree height per plot scover standardized percentage of canopy cover per plot The stripped cone count was only taken when the mean diameter of trees was under 0.6m (dbh). ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/nuts.csv", + "filename": "nuts", + "name": "nuts", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Numbers of aberrant crypt foci (ACF) in the section 1 of the colons of 22 rats subjected to a single dose of the carcinogen azoxymethane (AOM), sacrificed at 3 different times. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/ACF1.csv", + "filename": "ACF1", + "name": "Aberrant Crypt Foci in Rat Colons", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The cfseal data frame has 30 rows and 11 columns consisting of weight measurements for various organs taken from 30 Cape Fur Seals that died as an unintended consequence of commercial fishing. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/cfseal.csv", + "filename": "cfseal", + "name": "Cape Fur Seal Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data are from trials that studied the mortality response of codling moth to fumigation with methyl bromide. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/codling.csv", + "filename": "codling", + "name": "Dose-mortality data, for fumigation of codling moth with methyl bromide", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data compare mean length, mean breadth, and egg color, between cuckoos and their hosts. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/cuckoohosts.csv", + "filename": "cuckoohosts", + "name": "Comparison of cuckoo eggs with host eggs", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Length and breadth measurements of 120 eggs lain in the nests of six different species of host bird. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/cuckoos.csv", + "filename": "cuckoos", + "name": "Cuckoo Eggs Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data record, for each of 2000 administrative regions, whether or not dengue was recorded at any time between 1961 and 1990. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/dengue.csv", + "filename": "dengue", + "name": "Dengue prevalence, by administrative region", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The fossum data frame consists of nine morphometric measurements on each of 43 female mountain brushtail possums, trapped at seven sites from Southern Victoria to central Queensland. This is a subset of the possum data frame. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/fossum.csv", + "filename": "fossum", + "name": "Female Possum Measurements", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The frogs data frame has 212 rows and 11 columns. The data are on the distribution of the Southern Corroboree frog, which occurs in the Snowy Mountains area of New South Wales, Australia. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/frogs.csv", + "filename": "frogs", + "name": "Frogs Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The kiwishade data frame has 48 rows and 4 columns. The data are from a designed experiment that compared different kiwifruit shading treatments. There are four vines in each plot, and four plots (one for each of four treatments: none, Aug2Dec, Dec2Feb, and Feb2May) in each of three blocks (locations: west, north, east). Each plot has the same number of vines, each block has the same number of plots, with each treatment occurring the same number of times. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/kiwishade.csv", + "filename": "kiwishade", + "name": "Kiwi Shading Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data on the body and brain weights of 20 mice, together with the size of the litter. Two mice were taken from each litter size. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/litters.csv", + "filename": "litters", + "name": "Mouse Litters", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The lung vector consists of weight measurements of lungs taken from 30 Cape Fur Seals that died as an unintended consequence of commercial fishing. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/lung.csv", + "filename": "lung", + "name": "Cape Fur Seal Lung Measurements", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The milk data frame has 17 rows and 2 columns. Each of 17 panelists compared two milk samples for sweetness. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/milk.csv", + "filename": "milk", + "name": "Milk Sweetness Study", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The moths data frame has 41 rows and 4 columns. These data are from a study of the effect of habitat on the densities of two species of moth (A and P). Transects were set across the search area. Within transects, sections were identified according to habitat type. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/moths.csv", + "filename": "moths", + "name": "Moths Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The possum data frame consists of nine morphometric measurements on each of 104 mountain brushtail possums, trapped at seven sites from Southern Victoria to central Queensland. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/possum.csv", + "filename": "possum", + "name": "Possum Measurements", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The possumsites data frame consists of Longitudes, Latitudes, and altitudes for the seven sites from Southern Victoria to central Queensland where the possum observations were made. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/possumsites.csv", + "filename": "possumsites", + "name": "Possum Sites", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A subset of Animals data frame from the MASS library. It contains the average body and brain measurements of five primates. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/primates.csv", + "filename": "primates", + "name": "Primate Body and Brain Weights", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The ChickWeight data frame has 578 rows and 4 columns from an experiment on the effect of diet on early growth of chicks. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/ChickWeight.csv", + "filename": "ChickWeight", + "name": "Weight versus age of chicks on different diets", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "An experiment was conducted to measure and compare the effectiveness of various feed supplements on the growth rate of chickens. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/chickwts.csv", + "filename": "chickwts", + "name": "Chicken Weights by Feed Type", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The DNase data frame has 176 rows and 3 columns of data obtained during development of an ELISA assay for the recombinant protein DNase in rat serum. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/DNase.csv", + "filename": "DNase", + "name": "Elisa assay of DNase", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The counts of insects in agricultural experimental units treated with different insecticides. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/InsectSprays.csv", + "filename": "InsectSprays", + "name": "Effectiveness of Insect Sprays", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Annual numbers of lynx trappings for 1821–1934 in Canada. Taken from Brockwell & Davis (1991), this appears to be the series considered by Campbell & Walker (1977). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/lynx.csv", + "filename": "lynx", + "name": "Annual Canadian Lynx trappings 1821–1934", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Animals" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Charles Darwin conducted an experiment to examine the superiority of cross-fertilized plants over self-fertilized plants. 15 pairs of plants were used. Each pair consisted of one cross-fertilized plant and one self-fertilized plant which germinated at the same time and grew in the same pot. The plants were measured at a fixed time after planting and the difference in heights between the cross- and self-fertilized plants are recorded in eighths of an inch.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/darwin.csv", + "filename": "darwin", + "name": "Darwin's Plant Height Differences ", + "number_format": 0, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The location of living bramble canes in a 9m square plot was recorded. We take 9m to be the unit of distance so that the plot can be thought of as a unit square. The bramble canes were also classified by their age. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/brambles.csv", + "filename": "brambles", + "name": "Spatial Location of Bramble Canes ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The cane data frame has 180 rows and 5 columns. The data frame represents a randomized block design with 45 varieties of sugar-cane and 4 blocks.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/cane.csv", + "filename": "cane", + "name": "Sugar-cane Disease Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The number of balsam-fir seedlings in each quadrant of a grid of 50 five foot square quadrants were counted. The grid consisted of 5 rows of 10 quadrants in each row. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/fir.csv", + "filename": "fir", + "name": "Counts of Balsam-fir Seedlings ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "8 characteristics for 18 popular flowers.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/flower.csv", + "filename": "flower", + "name": "Flower Characteristics", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This dataset constitutes a description of 136 plant species according to biological attributes (morphological or reproductive) ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/plantTraits.csv", + "filename": "plantTraits", + "name": "Plant Species Traits Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data frames have averages by blocks (parcels) for the treatment 111. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/ant111b.csv", + "filename": "ant111b", + "name": "Averages by block of corn yields, for treatment 111 only", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data frames have yield averages by blocks (parcels). The ant111b data set is a subset of this. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/antigua.csv", + "filename": "antigua", + "name": "Averages by block of yields for the Antigua Corn data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Each of 20 tasters each assessed three out of the four varieties. The experiment was conducted according to a balanced incomplete block design. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/appletaste.csv", + "filename": "appletaste", + "name": "Tasting experiment that compared four apple varieties", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The biomass data frame has 135 rows and 8 columns. The rainforest data frame is a subset of this one. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/biomass.csv", + "filename": "biomass", + "name": "Biomass Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data are from a study that examined how the electrical resistance of a slab of kiwifruit changed with the apparent juice content. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/fruitohms.csv", + "filename": "fruitohms", + "name": "Electrical Resistance of Kiwi Fruit", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Leaf length, width and petiole measurements taken at various sites in Australia. ", + "download": "http://vincentarelbundock.github.io/Rdatasets/csv/DAAG/leafshape.csv", + "filename": "leafshape", + "name": "Full Leaf Shape Data Set", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The leafshape17 data frame has 61 rows and 8 columns. These are leaf length, width and petiole measurements taken at several sites in Australia. This is a subset of the leafshape data frame. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/leafshape17.csv", + "filename": "leafshape17", + "name": "Subset of Leaf Shape Data Set", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data consist of measurements of vapour pressure and of the difference between leaf and air temperature. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/leaftemp.csv", + "filename": "leaftemp", + "name": "Leaf and Air Temperature Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The leaftemp.all data frame has 62 rows and 9 columns. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/leaftemp.all.csv", + "filename": "leaftempAll", + "name": "Full Leaf and Air Temperature Data Set", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data which compare the heights of crossed plants with self-fertilized plants. Plants were paired within the pots in which they were grown, with one on one side and one on the other. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/mignonette.csv", + "filename": "mignonette", + "name": "Darwin's Wild Mignonette Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The rainforest data frame has 65 rows and 7 columns. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/rainforest.csv", + "filename": "rainforest", + "name": "Rainforest Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data were taken from species lists for South Australia, Victoria and Tasmania. Species were classified as CC, CR, RC and RR, with C denoting common and R denoting rare. The first code relates to South Australia and Victoria, and the second to Tasmania. They were further classified by habitat according to the Victorian register, where D = dry only, W = wet only, and WD = wet or dry. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/rareplants.csv", + "filename": "rareplants", + "name": "Rare and Endangered Plant Species", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The rice data frame has 72 rows and 7 columns. The data are from an experiment that compared wild type (wt) and genetically modified rice plants (ANU843), each with three different chemical treatments (F10, NH4Cl, and NH4NO3). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/rice.csv", + "filename": "rice", + "name": "Genetically Modified and Wild Type Rice Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The roller data frame has 10 rows and 2 columns. Different weights of roller were rolled over different parts of a lawn, and the depression was recorded. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/roller.csv", + "filename": "roller", + "name": "Lawn Roller Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The seedrates data frame has 5 rows and 2 columns on the effect of seeding rate of barley on yield. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/seedrates.csv", + "filename": "seedrates", + "name": "Barley Seeding Rate Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Concentration-time measurements on different varieties of apples under methyl bromide injection. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/sorption.csv", + "filename": "sorption", + "name": "sorption data set", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data frames have yield averages by blocks (parcels). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/stVincent.csv", + "filename": "stVincent", + "name": "Averages by block of yields for the St. Vincent Corn data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The sugar data frame has 12 rows and 2 columns. They are from an experiment that compared an unmodified wild type plant with three different genetically modified forms. The measurements are weights of sugar that were obtained by breaking down the cellulose. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/sugar.csv", + "filename": "sugar", + "name": "Description", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The tomato data frame has 24 rows and 2 columns. They are from an experiment that exposed tomato plants to four different 'nutrients'. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/tomato.csv", + "filename": "tomato", + "name": "Root weights of tomato plants exposed to 4 different treatments", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data frames have averages by blocks (parcels) for the treatment 111. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/vince111b.csv", + "filename": "vince111b", + "name": "Averages by block of corn yields, for treatment 111 only", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This famous (Fisher's or Anderson's) iris data set gives the measurements in centimeters of the variables sepal length and width and petal length and width, respectively, for 50 flowers from each of 3 species of iris. The species are Iris setosa, versicolor, and virginica. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv", + "filename": "iris", + "name": "Edgar Anderson's Iris Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This famous (Fisher's or Anderson's) iris data set gives the measurements in centimeters of the variables sepal length and width and petal length and width, respectively, for 50 flowers from each of 3 species of iris. The species are Iris setosa, versicolor, and virginica. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/iris3.csv", + "filename": "iris3", + "name": "Edgar Anderson's Iris Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Loblolly data frame has 84 rows and 3 columns of records of the growth of Loblolly pine trees. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/Loblolly.csv", + "filename": "Loblolly", + "name": "Growth of Loblolly pine trees", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Plants" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data values are monthly averages of the daily stages (heights) of the Rio Negro at Manaus. Manaus is 18km upstream from the confluence of the Rio Negro with the Amazon but because of the tiny slope of the water surface and the lower courses of its flatland affluents, they may be regarded as a good approximation of the water level in the Amazon at the confluence. The data here cover 90 years from January 1903 until December 1992. \nThe Manaus gauge is tied in with an arbitrary bench mark of 100m set in the steps of the Municipal Prefecture; gauge readings are usually referred to sea level, on the basis of a mark on the steps leading to the Parish Church (Matriz), which is assumed to lie at an altitude of 35.874 m according to observations made many years ago under the direction of Samuel Pereira, an engineer in charge of the Manaus Sanitation Committee Whereas such an altitude cannot, by any means, be considered to be a precise datum point, observations have been provisionally referred to it. The measurements are in metres. \n", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/manaus.csv", + "filename": "manaus", + "name": "Average Heights of the Rio Negro river at Manaus", + "number_format": 0, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Nitrofen is a herbicide that was used extensively for the control of broad-leaved and grass weeds in cereals and rice. Although it is relatively non-toxic to adult mammals, nitrofen is a significant tetragen and mutagen. It is also acutely toxic and reproductively toxic to cladoceran zooplankton. Nitrofen is no longer in commercial use in the U.S., having been the first pesticide to be withdrawn due to tetragenic effects. \nThe data here come from an experiment to measure the reproductive toxicity of nitrofen on a species of zooplankton (Ceriodaphnia dubia). 50 animals were randomized into batches of 10 and each batch was put in a solution with a measured concentration of nitrofen. Then the number of live offspring in each of the three broods to each animal was recorded. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/nitrofen.csv", + "filename": "nitrofen", + "name": "Toxicity of Nitrofen in Aquatic Systems ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Biweekly averages of the water salinity and river discharge in Pamlico Sound, North Carolina were recorded between the years 1972 and 1977. The data in this set consists only of those measurements in March, April and May. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/salinity.csv", + "filename": "salinity", + "name": "Water Salinity and River Discharge ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Heights, stored as a multivariate time series, are for the lakes Erie, Michigan/Huron, Ontario and St Clair ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/greatLakes.csv", + "filename": "greatLakes", + "name": " Yearly averages of Great Lake heights: 1918 - 2009 ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Manitoba.lakes data frame has 9 rows and 2 columns. The areas and elevations of the nine largest lakes in Manitoba, Canada. The geography of Manitoba (a relatively flat province) can be divided crudely into three main areas: a very flat prairie in the south which is at a relatively high elevation, a middle region consisting of mainly of forest and Precambrian rock, and a northern region which drains more rapidly into Hudson Bay. All water in Manitoba, which does not evaporate, eventually drains into Hudson Bay. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/Manitoba.lakes.csv", + "filename": "ManitobaLakes", + "name": "The Nine Largest Lakes in Manitoba", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Annual measurements of the level, in feet, of Lake Huron 1875–1972. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/LakeHuron.csv", + "filename": "LakeHuron", + "name": "Level of Lake Huron 1875–1972", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Rivers" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data are the pole positions from a paleomagnetic study of New Caledonian laterites. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/polar.csv", + "filename": "polar", + "name": "Pole Positions of New Caledonian Laterites ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Southern Oscillation Index (SOI) is the difference in barometric pressure at sea level between Tahiti and Darwin. Annual SOI and Australian rainfall data, for the years 1900-2001, are given. Australia's annual mean rainfall is an area-weighted average of the total annual precipitation at approximately 370 rainfall stations around the country. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/bomsoi.csv", + "filename": "bomsoi", + "name": "Southern Oscillation Index Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The geophones data frame has 56 rows and 2 columns. Thickness of a layer of Alberta substratum as measured by a line of geophones. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/geophones.csv", + "filename": "geophones", + "name": "Seismic Timing Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "K-Ar Ages (millions of years) and distances (km) from Kilauea along the trend of the chain of Hawaian volcanic islands and other seamounts that are believed to have been created by a moving \"hot spot\". The age of Kilauea is given as 0-0.4 Ma. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/hotspots.csv", + "filename": "hotspots", + "name": "Hawaian island chain hotspot Potassium-Argon ages", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Ar-Ar Ages (millions of years) and distances (km) from Kilauea along the trend of the chain of Hawaian volcanic islands and other seamounts that are believed to have been created by a moving \"hot spot\". ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/hotspots2006.csv", + "filename": "hotspots2006", + "name": "Hawaian island chain hotspot Argon-Argon ages", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data characterise rock art at 103 sites in the Pacific. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/rockArt.csv", + "filename": "rockArt", + "name": "Pacific Rock Art features", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data gives peak accelerations measured at various observation stations for 23 earthquakes in California. The data have been used by various workers to estimate the attenuating affect of distance on ground acceleration. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/attenu.csv", + "filename": "attenu", + "name": "The Joyner–Boore Attenuation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Geology" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data collected at Winnipeg International Airport (Canada) on periods (in days) between rain events. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/droughts.csv", + "filename": "droughts", + "name": "Periods Between Rain Events", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Carbon dioxide record from the EPICA (European Project for Ice Coring in Antarctica) Dome C ice core covering 0 to 800 kyr BP. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/edcCO2.csv", + "filename": "edcCO2", + "name": "EPICA Dome C Ice Core 800KYr Carbon Dioxide Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Temperature record, using Deuterium as a proxy, from the EPICA (European Project for Ice Coring in Antarctica) Dome C ice core covering 0 to 800 kyr BP. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/edcT.csv", + "filename": "edcT", + "name": "EPICA Dome C Ice Core 800KYr Temperature Estimates", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Details are given of atmospheric pressure at landfall, estimated damage in millions of dollars, and deaths, for named hurricanes that made landfall in the US mainland from 1950 through to 2012. ", + "download": "http://vincentarelbundock.github.io/Rdatasets/csv/DAAG/hurricNamed.csv", + "filename": "hurricNamed", + "name": " Named US Atlantic Hurricanes ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Monthly provisional mean total ozone (in Dobson units) at Halley Bay (approximately corrected to Bass-Paur). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/ozone.csv", + "filename": "ozone", + "name": "Ozone Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Daily air quality measurements in New York, May to September 1973. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/airquality.csv", + "filename": "airquality", + "name": "New York Air Quality Measurements", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Atmospheric concentrations of CO2 are expressed in parts per million (ppm) and reported in the preliminary 1997 SIO manometric mole fraction scale. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/CO2.csv", + "filename": "co2", + "name": "Mauna Loa Atmospheric CO2 Concentration", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Waiting time between eruptions and the duration of the eruption for the Old Faithful geyser in Yellowstone National Park, Wyoming, USA. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/faithful.csv", + "filename": "faithful", + "name": "Old Faithful Geyser Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Other" + } + ] + }, + { + "category_name": "Statistics", + "subcategories": [ + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The measurements are the population (in 1000's) of 49 U.S. cities in 1920 and 1930. The 49 cities are a random sample taken from the 196 largest cities in 1920. The city data frame consists of the first 10 observations in bigcity.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/bigcity.csv", + "filename": "bigcity", + "name": "Population of U.S. Cities", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "column_description_0": "index", + "column_description_1": "census year. ", + "column_description_2": "Population, in millions ", + "comment_character": "#", + "create_index_column": false, + "description": "The CanPop data frame has 16 rows and 2 columns. Decennial time-series of Canadian population, 1851–2001. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/CanPop.csv", + "filename": "CanPop", + "name": "Canadian Population Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Channing House is a retirement centre in Palo Alto, California. These data were collected between the opening of the house in 1964 until July 1, 1975. In that time 97 men and 365 women passed through the centre. For each of these, their age on entry and also on leaving or death was recorded. A large number of the observations were censored mainly due to the resident being alive on July 1, 1975 when the data was collected. Over the time of the study 130 women and 46 men died at Channing House. Differences between the survival of the sexes, taking age into account, was one of the primary concerns of this study. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/channing.csv", + "filename": "channing", + "name": " Channing House Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The measurements are the population (in 1000's) of 49 U.S. cities in 1920 and 1930. The 49 cities are a random sample taken from the 196 largest cities in 1920. The city data frame consists of the first 10 observations in bigcity. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/city.csv", + "filename": "city", + "name": "Population of U.S. Cities ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Angell data frame has 43 rows and 4 columns. The observations are 43 U. S. cities around 1950. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Angell.csv", + "filename": "Angell", + "name": "Moral Integration of American Cities", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Anscombe data frame has 51 rows and 4 columns. The observations are the U. S. states plus Washington, D. C. in 1970. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Anscombe.csv", + "filename": "Anscombe", + "name": "U. S. State Public-School Expenditures", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Chirot data frame has 32 rows and 5 columns. The observations are counties in Romania. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Chirot.csv", + "filename": "Chirot", + "name": "The 1907 Romanian Peasant Rebellion", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Duncan data frame has 45 rows and 4 columns. Data on the prestige and other characteristics of 45 U. S. occupations in 1950. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Duncan.csv", + "filename": "Duncan", + "name": "Duncan's Occupational Prestige Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Ericksen data frame has 66 rows and 9 columns. The observations are 16 large cities, the remaining parts of the states in which these cities are located, and the other U. S. states. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Ericksen.csv", + "filename": "Ericksen", + "name": "The 1980 U.S. Census Undercount", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Leinhardt data frame has 105 rows and 4 columns. The observations are nations of the world around 1970. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Leinhardt.csv", + "filename": "Leinhardt", + "name": "Data on Infant-Mortality", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Migration data frame has 90 rows and 8 columns. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Migration.csv", + "filename": "Migration", + "name": "Canadian Interprovincial Migration Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Minneapolis Demographic Data 2015, by Neighborhood, from the 2015 American Community Survey ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/MplsDemo.csv", + "filename": "MplsDemo", + "name": " Minneapolis Demographic Data 2015, by Neighborhood ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The States data frame has 51 rows and 8 columns. The observations are the U. S. states and Washington, D. C. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/States.csv", + "filename": "States", + "name": "Education and Related Statistics for the U.S. States", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "National health, welfare, and education statistics for 213 places, mostly UN members, but also other areas like Hong Kong that are not independent countries. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/UN.csv", + "filename": "UN", + "name": " National Statistics from the United Nations, Mostly From 2009–2011 ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Social indicators data on 207 nations distributed by the United Nations circa 1998. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/UN98.csv", + "filename": "UN98", + "name": " United Nations Social Indicators Data 1998] ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The USPop data frame has 22 rows and 1 columns. This is a decennial time-series, from 1790 to 2000. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/USPop.csv", + "filename": "USPop", + "name": "Population of the United States", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Vocab data frame has 30,351 rows and 4 columns. The observations are respondents to U.S. General Social Surveys, 1972-2016. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Vocab.csv", + "filename": "Vocab", + "name": "Vocabulary and Education", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data on whether or not households in Bangladesh changed the wells that they were using. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Wells.csv", + "filename": "Wells", + "name": "Well Switching in Bangladesh", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Latitudes and longitudes for Adelaide, Alice, Brisbane, Broome, Cairns, Canberra, Darwin, Melbourne, Perth and Sydney; i.e., for the cities to which the road distances in audists relate. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/aulatlong.csv", + "filename": "aulatlong", + "name": "Latitudes and longitudes for ten Australian cities", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Population figures for Australian states and territories for 1917, 1927, ..., 1997. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/austpop.csv", + "filename": "austpop", + "name": "Population figures for Australian States and Territories", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Australian regional temperature data, Australian regional rainfall data, and Annual SOI, are given for the years 1900-2008 or 1900-2011 or 1900-2012. The regional rainfall and temperature data are area-weighted averages for the respective regions. The Southern Oscillation Index (SOI) is the difference in barometric pressure at sea level between Tahiti and Darwin. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/bomregions.csv", + "filename": "bomregions", + "name": "Australian and Related Historical Annual Climate Data, by region", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Australian regional temperature data, Australian regional rainfall data, and Annual SOI, are given for the years 1900-2008 or 1900-2011 or 1900-2012. The regional rainfall and temperature data are area-weighted averages for the respective regions. The Southern Oscillation Index (SOI) is the difference in barometric pressure at sea level between Tahiti and Darwin. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/bomregions2011.csv", + "filename": "bomregions2011", + "name": "Australian and Related Historical Annual Climate Data, by region", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Australian regional temperature data, Australian regional rainfall data, and Annual SOI, are given for the years 1900-2008 or 1900-2011 or 1900-2012. The regional rainfall and temperature data are area-weighted averages for the respective regions. The Southern Oscillation Index (SOI) is the difference in barometric pressure at sea level between Tahiti and Darwin. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/bomregions2012.csv", + "filename": "bomregions2012", + "name": "Australian and Related Historical Annual Climate Data, by region", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The corrected Boston housing data (from http://lib.stat.cmu.edu/datasets/). ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/bostonc.csv", + "filename": "bostonc", + "name": "Boston Housing Data – Corrected", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Population estimates for several Canadian cities. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/cities.csv", + "filename": "cities", + "name": "Populations of Major Canadian Cities (1992-96)", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The science data frame has 1385 rows and 7 columns. \nThe data are on attitudes to science, from a survey where there were results from 20 classes in private schools and 46 classes in public schools. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/science.csv", + "filename": "science", + "name": "School Science Survey Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Numbers (in thousands) of Australian residents measured quarterly from March 1971 to March 1994. The object is of class \"ts\". ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/austres.csv", + "filename": "austres", + "name": " Quarterly Time Series of the Number of Australian Residents ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Distribution of hair and eye color and sex in 592 statistics students. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/HairEyeColor.csv", + "filename": "HairEyeColor", + "name": "Hair and Eye Color of Statistics Students", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The areas in thousands of square miles of the landmasses which exceed 10,000 square miles. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/islands.csv", + "filename": "islands", + "name": "Areas of the World's Major Landmasses", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Demographics" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "In a study into the effect that warning signs have on speeding patterns, Cambridgeshire County Council considered 14 pairs of locations. The locations were paired to account for factors such as traffic volume and type of road. One site in each pair had a sign erected warning of the dangers of speeding and asking drivers to slow down. No action was taken at the second site. Three sets of measurements were taken at each site. Each set of measurements was nominally of the speeds of 100 cars but not all sites have exactly 100 measurements. These speed measurements were taken before the erection of the sign, shortly after the erection of the sign, and again after the sign had been in place for some time. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/amis.csv", + "filename": "amis", + "name": "Car Speeding and Warning Signs ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Proschan (1963) reported on the times between failures of the air-conditioning equipment in 10 Boeing 720 aircraft. The aircondit data frame contains the intervals for the ninth aircraft while aircondit7 contains those for the seventh aircraft. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/aircondit.csv", + "filename": "aircondit", + "name": "Failures of Air-conditioning Equipment ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Proschan (1963) reported on the times between failures of the air-conditioning equipment in 10 Boeing 720 aircraft. The aircondit data frame contains the intervals for the ninth aircraft while aircondit7 contains those for the seventh aircraft. \nBoth data frames have just one column. Note that the data have been sorted into increasing order. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/aircondit7.csv", + "filename": "aircondit7", + "name": "Failures of Air-conditioning Equipment ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The motor data frame has 94 rows and 4 columns. The rows are obtained by removing replicate values of time from the dataset mcycle. Two extra columns are added to allow for strata with a different residual variance in each stratum. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/motor.csv", + "filename": "motor", + "name": "Data from a Simulated Motorcycle Accident", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data comes from a unpublished master's paper by Carl Hoffstedt. They relate the automobile accident rate, in accidents per million vehicle miles to several potential terms. The data include 39 sections of large highways in the state of Minnesota in 1973. The goal of this analysis was to understand the impact of design variables, Acpts, Slim, Sig, and Shld that are under the control of the highway department, on accidents. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Highway1.csv", + "filename": "Highway1", + "name": "Highway Accidents", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data set used in McCullagh & Nelder (1989), Hardin & Hilbe (2003), and other sources. The data contains values on the number of reported accidents for ships belonging to a company over a given time period. When a ship was constructed is also recorded. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/ships.csv", + "filename": "ships", + "name": "ships", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data is an observation-based version of the 1912 Titanic passenger survival log, ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/titanic.csv", + "filename": "titanic", + "name": "titanic", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data is an grouped version of the 1912 Titanic passenger survival log, ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/titanicgrp.csv", + "filename": "titanicgrp", + "name": "titanicgrp", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A non-experimental \"control\" group, used in various studies of the effect of a labor training program, alternative to the experimental control group in nswdemo. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/cps3.csv", + "filename": "cps3", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Estimates of total worldwide carbon emissions from fossil fuel use. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/fossilfuel.csv", + "filename": "fossilfuel", + "name": "Fossil Fuel Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The record times in 1984 for 35 Scottish hill races. ", + "download": "http://vincentarelbundock.github.io/Rdatasets/csv/DAAG/hills.csv", + "filename": "hills", + "name": "Scottish Hill Races Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "US data, for 1997-2002, from police-reported car crashes in which there is a harmful event (people or property), and from which at least one vehicle was towed. Data are restricted to front-seat occupants, include only a subset of the variables recorded, and are restricted in other ways also.", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nassCDS.csv", + "filename": "nassCDS", + "name": "Airbag and other influences on accident fatalities", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Progression in world record times for track and road races.", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/progression.csv", + "filename": "progression", + "name": "Progression of Record times for track races, 1912 - 2008", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The record times in 2000 for 77 Scottish long distance races. We believe the data are, for the most part, trustworthy. However, the dist variable for Caerketton (record 58) seems to have been variously recorded as 1.5 mi and 2.5 mi. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/races2000.csv", + "filename": "races2000", + "name": "Scottish Hill Races Data - 2000", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data are from an experiment that aimed to model the effects of the tinting of car windows on visual performance. The authors were mainly interested in effects on side window vision, and hence in visual recognition tasks that would be performed when looking through side windows. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/tinting.csv", + "filename": "tinting", + "name": "Car Window Tinting Experiment Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Record times for track and road races, at August 9th 2006", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/worldRecords.csv", + "filename": "worldRecords", + "name": "Record times for track and road races, at August 9th 2006", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The revenue passenger miles flown by commercial airlines in the United States for each year from 1937 to 1960. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/airmiles.csv", + "filename": "airmiles", + "name": "Passenger Miles on Commercial US Airlines, 1937–1960", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The classic Box & Jenkins airline data. Monthly totals of international airline passengers, 1949 to 1960. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/AirPassengers.csv", + "filename": "AirPassengers", + "name": "Monthly Airline Passenger Numbers 1949-1960", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data give the speed of cars and the distances taken to stop. Note that the data were recorded in the 1920s. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/cars.csv", + "filename": "cars", + "name": "Speed and Stopping Distances of Cars", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data was extracted from the 1974 Motor Trend US magazine, and comprises fuel consumption and 10 aspects of automobile design and performance for 32 automobiles (1973–74 models). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/mtcars.csv", + "filename": "mtcars", + "name": "Motor Trend Car Road Tests", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Traffic" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The excess return for the Acme Cleveland Corporation are recorded along with those for all stocks listed on the New York and American Stock Exchanges were recorded over a five year period. These excess returns are relative to the return on a risk-less investment such a U.S. Treasury bills. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/acme.csv", + "filename": "acme", + "name": "Monthly Excess Returns", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data relate to the construction of 32 light water reactor (LWR) plants constructed in the U.S.A in the late 1960's and early 1970's. The data was collected with the aim of predicting the cost of construction of further LWR plants. 6 of the power plants had partial turnkey guarantees and it is possible that, for these plants, some manufacturers' subsidies may be hidden in the quoted capital costs. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/nuclear.csv", + "filename": "nuclear", + "name": " Nuclear Power Station Construction Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Each week that the market is open the Australian Wool Corporation set a floor price which determines their policy on intervention and is therefore a reflection of the overall price of wool for the week in question. Actual prices paid can vary considerably about the floor price. The series here is the log of the ratio between the price for fine grade wool and the floor price, each market week between July 1976 and Jun 1984. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/wool.csv", + "filename": "wool", + "name": " Australian Relative Wool Prices ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Mroz data frame has 753 rows and 8 columns. The observations, from the Panel Study of Income Dynamics (PSID), are married women. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Mroz.csv", + "filename": "Mroz", + "name": "U.S. Women's Labor-Force Participation", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Ornstein data frame has 248 rows and 4 columns. The observations are the 248 largest Canadian firms with publicly available information in the mid-1970s. The names of the firms were not available. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Ornstein.csv", + "filename": "Ornstein", + "name": "Interlocking Directorates Among Major Canadian Firms", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Prestige data frame has 102 rows and 6 columns. The observations are occupations. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Prestige.csv", + "filename": "Prestige", + "name": "Prestige of Canadian Occupations", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Sahlins data frame has 20 rows and 2 columns. The observations are households in a Central African village. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Sahlins.csv", + "filename": "Sahlins", + "name": "Agricultural Production in Mazulu Village", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The 2008-09 nine-month academic salary for Assistant Professors, Associate Professors and Professors in a college in the U.S. The data were collected as part of the on-going effort of the college's administration to monitor salary differences between male and female faculty members. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Salaries.csv", + "filename": "Salaries", + "name": " Salaries for Professors ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The SLID data frame has 7425 rows and 5 columns. The data are from the 1994 wave of the Canadian Survey of Labour and Income Dynamics, for the province of Ontario. There are missing data, particularly for wages. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/SLID.csv", + "filename": "SLID", + "name": "Survey of Labour and Income Dynamics", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data on transaction times in branch offices of a large Australian bank. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Transact.csv", + "filename": "Transact", + "name": "Transaction data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Womenlf data frame has 263 rows and 4 columns. The data are from a 1977 survey of the Canadian population. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Womenlf.csv", + "filename": "Womenlf", + "name": "Canadian Women's Labour-Force Participation", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Gross National Product (GNP) per capita and percentage of the population working in agriculture for each country belonging to the European Union in 1993. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/agriculture.csv", + "filename": "agriculture", + "name": "European Union Agricultural Workforces", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data from a subset of the German Socio-Economic Panel (SOEP). The subset was created by Rabe-Hesketh and Skrondal (2005). Only working women are included in these data. Beginning in 1997, German health reform in part entailed a 200 co-payment as well as limits in provider reimbursement. Patients were surveyed for the one year panel (1996) prior to and the one year panel (1998) after reform to assess whether the number of physician visits by patients declined - which was the goal of reform legislation. The response, or variable to be explained by the model, is numvisit, which indicates the number of patient visits to a physician's office during a three month period. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/mdvis.csv", + "filename": "mdvis", + "name": "mdvis", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "U.S. data extracted from Cars93, a data frame in the MASS package. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/carprice.csv", + "filename": "carprice", + "name": "US Car Price Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Cars93.summary data frame has 6 rows and 4 columns created from information in the Cars93 data set in the Venables and Ripley MASS package. Each row corresponds to a different class of car (e.g. Compact, Large, etc.). ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/Cars93.summary.csv", + "filename": "Cars93Summary", + "name": "A Summary of the Cars93 Data set", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Numbers are given in different categories of worker, in each of two investigations. The first source of information is the Board of Trade Census that was conducted on 1886. The second is a relatively informal survey conducted by US Bureau of Labor representatives in 1889, for use in official reports. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/cottonworkers.csv", + "filename": "cottonworkers", + "name": "Occupation and wage profiles of British cotton workers", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data are annual apparent alcohol consumption in Australia and New Zealand, in liters of pure alcohol content per annum, separately for beer, wine, and spirits (including spirit-based products). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/grog.csv", + "filename": "grog", + "name": "Alcohol consumption in Australia and New Zealand", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The houseprices data frame consists of the floor area, price, and the number of bedrooms for a sample of houses sold in Aranda in 1999. Aranda is a suburb of Canberra, Australia. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/houseprices.csv", + "filename": "houseprices", + "name": "Aranda House Prices", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The number of workers in the Canadian labour force broken down by region (BC, Alberta, Prairies, Ontario, Quebec, Atlantic) for the 24-month period from January, 1995 to December, 1996 (a time when Canada was emerging from a deep economic recession). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/jobs.csv", + "filename": "jobs", + "name": "Canadian Labour Force Summary Data (1995-96)", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data frame Lottario is a summary of 122 weekly draws of an Ontario lottery, beginning in November, 1978. Each draw consists of 7 numbered balls, drawn without replacement from an urn consisting of balls numbered from 1 through 39. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/Lottario.csv", + "filename": "Lottario", + "name": "Ontario Lottery Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The medExpenses data frame contains average weekly medical expenses including drugs for 33 families randomly sampled from a community of 600 families which contained 2700 individuals. These data were collected in the 1970's at an unknown location. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/medExpenses.csv", + "filename": "medExpenses", + "name": "Family Medical Expenses", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data frame contains 445 rows and 10 columns. These data are from an investigation of the effect of training on changes, between 1974-1975 and 1978, in the earnings of individuals who had experienced employment difficulties Data are for the male experimental control and treatment groups. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nsw74demo.csv", + "filename": "nsw74demo", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data frame contains 2675 rows and 10 columns. These data are pertinent to an investigation of the way that earnings changed, between 1974-1975 and 1978, in the absence of training. Data for the experimental treatment group (NSW) were combined with control data results from the Panel Study of Income Dynamics (PSID) study. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nsw74psid1.csv", + "filename": "nsw74psid1", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data are pertinent to an investigation of the way that earnings changed, between 1974-1975 and 1978, in the absence of training. The data frame combines data for the experimental treatment group (NSW, 185 observations), using as control data results from the PSID (Panel Study of Income Dynamics) study (128 observations). The latter were chosen to mimic the characteristics of the NSW training and control groups. These are a subset of the nsw74psid1 data. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nsw74psid3.csv", + "filename": "nsw74psid3", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The nsw74psidA data frame has 252 rows and 10 columns. See nsw74psid1 for more information. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nsw74psidA.csv", + "filename": "nsw74psidA", + "name": "A Subset of the nsw74psid1 Data Set", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The nswdemo data frame contains 722 rows and 10 columns. These data are pertinent to an investigation of the way that earnings changed, between 1974-1975 and 1978, for an experimental treatment who were given job training as compared with a control group who did not receive such training. \nThe psid1 data set is an alternative non-experimental \"control\" group. psid2 and psid3 are subsets of psid1, designed to be better matched to the experimental data than psid1. Note also the cps1, cps2 and cps3 datasets (DAAGxtras) that have been proposed as non-experimental controls. \n", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nswdemo.csv", + "filename": "nswdemo", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data frame contains 2787 rows and 10 columns. These data are pertinent to an investigation of the way that earnings changed, between 1974-1975 and 1978, in the absence of training. Data for the experimental treatment group in nswdemo are combined with the psid1 control data from the Panel Study of Income Dynamics (PSID) study. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nswpsid1.csv", + "filename": "nswpsid1", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A non-experimental \"control\" group, used in various studies of the effect of a labor training program, alternative to the experimental control group in nswdemo. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/psid1.csv", + "filename": "psid1", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A non-experimental \"control\" group, used in various studies of the effect of a labor training program, alternative to the experimental control group in nswdemo. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/psid2.csv", + "filename": "psid2", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A non-experimental \"control\" group, used in various studies of the effect of a labor training program, alternative to the experimental control group in nswdemo. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/psid3.csv", + "filename": "psid3", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data from a survey on social and other kinds of support. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/socsupport.csv", + "filename": "socsupport", + "name": "Social Support Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data on objects appearing in three windows on a video lottery terminal, together with the prize payout (usually 0). Observations were taken on two successive days in late 1994 at a hotel lounge north of Winnipeg, Manitoba. Each observation cost 25 cents (Canadian). The game played was ‘Double Diamond’. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/vlt.csv", + "filename": "vlt", + "name": "Video Lottery Terminal Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The wages1833 data frame gives the wages of Lancashire cotton factory workers in 1833. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/wages1833.csv", + "filename": "wages1833", + "name": "Wages of Lancashire Cotton Factory Workers in 1833", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "From a survey of the clerical employees of a large financial organization, the data are aggregated from the questionnaires of the approximately 35 employees for each of 30 (randomly selected) departments. The numbers give the percent proportion of favourable responses to seven questions in each department.", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/attitude.csv", + "filename": "attitude", + "name": "The Chatterjee–Price Attitude Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The sales time series BJsales and leading indicator BJsales.lead each contain 150 observations. The objects are of class \"ts\". ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/BJsales.csv", + "filename": "BJsales", + "name": "Sales Data with Leading Indicator", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Conversion rates between the various Euro currencies.", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/euro.csv", + "filename": "euro", + "name": "Conversion Rates of Euro Currencies", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Contains the daily closing prices of major European stock indices: Germany DAX (Ibis), Switzerland SMI, France CAC, and UK FTSE. The data are sampled in business time, i.e., weekends and holidays are omitted. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/EuStockMarkets.csv", + "filename": "EuStockMarkets", + "name": " Daily Closing Prices of Major European Stock Indices, 1991–1998 ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Quarterly earnings (dollars) per Johnson & Johnson share 1960–80. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/JohnsonJohnson.csv", + "filename": "JohnsonJohnson", + "name": "Quarterly Earnings per Johnson & Johnson Share", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data on the savings ratio 1960–1970. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/LifeCycleSavings.csv", + "filename": "LifeCycleSavings", + "name": "Intercountry Life-Cycle Savings Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A macroeconomic data set which provides a well-known example for a highly collinear regression. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/longley.csv", + "filename": "longley", + "name": "Longley's Economic Regression Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Economics" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data are simulated successive observations from a process in equilibrium. The process is assumed to have specification limits (5.49, 5.79). ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/capability.csv", + "filename": "capability", + "name": "Simulated Manufacturing Process Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The cloth data frame has 32 rows and 2 columns. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/cloth.csv", + "filename": "cloth", + "name": "Number of Flaws in Cloth ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data frame gives the dates of 191 explosions in coal mines which resulted in 10 or more fatalities. The time span of the data is from March 15, 1851 until March 22 1962. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/coal.csv", + "filename": "coal", + "name": "Dates of Coal Mining Disasters ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The “experimenters” were the actual subjects of the study. They collected ratings of the apparent success of people in pictures who were pre-selected for their average appearance of success. The experimenters were told prior to collecting data that particular subjects were either high or low in their tendency to rate appearance of success, and were instructed to get good data, scientific data, or were given no such instruction. Each experimenter collected ratings from 18 randomly assigned subjects. This version of the Adler data is taken from Erickson and Nosanchuk (1977). The data described in the original source, Adler (1973), have a more complex structure. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Adler.csv", + "filename": "Adler", + "name": "Experimenter Expectations", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Counts of new PhDs in the mathematical sciences for 2008-09 and 2011-12 categorized by type of institution, gender, and US citizenship status. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/AMSsurvey.csv", + "filename": "AMSsurvey", + "name": " American Math Society Survey Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Baumann data frame has 66 rows and 6 columns. The data are from an experimental study conducted by Baumann and Jones, as reported by Moore and McCabe (1993) Students were randomly assigned to one of three experimental groups. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Baumann.csv", + "filename": "Baumann", + "name": "Methods of Teaching Reading Comprehension", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Mandel data frame has 8 rows and 3 columns. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Mandel.csv", + "filename": "Mandel", + "name": "Contrived Collinear Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Quartet data frame has 11 rows and 5 columns. These are contrived data. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Quartet.csv", + "filename": "Quartet", + "name": "Four Regression Datasets", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Information on the survival status, sex, age, and passenger class of 1309 passengers in the Titanic disaster of 1912. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/TitanicSurvival.csv", + "filename": "TitanicSurvival", + "name": "Survival of Passengers on the Titanic", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data from the World Values Surveys 1995-1997 for Australia, Norway, Sweden, and the United States. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/WVS.csv", + "filename": "WVS", + "name": "World Values Surveys", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This is a small rounded subset of the C-horizon data chorizon from package mvoutlier. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/chorSub.csv", + "filename": "chorSub", + "name": "Subset of C-horizon of Kola Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Ruspini data set, consisting of 75 points in four groups that is popular for illustrating clustering techniques. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/ruspini.csv", + "filename": "ruspini", + "name": "Ruspini Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "An artificial data set consisting of 3000 points in 3 quite well-separated clusters. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/xclara.csv", + "filename": "xclara", + "name": "Bivariate Data Set with 3 Clusters", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data from Fair (1978). Although Fair used a tobit model with the data, the outcome measure can be modeled as a count. In fact, Greene (2003) modeled it as Poisson, but given the amount of overdispersion in the data, employing a negative binomial model is an appropriate strategy. The data is stored in the affairs data set. Naffairs is the response variable, indicating the number of affairs reported by the participant in the past year. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/affairs.csv", + "filename": "affairs", + "name": "affairs", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data are taken from Loomis (2003). The study relates to a survey taken on reported frequency of visits to national parks during the year. The survey was taken at park sites, thus incurring possible effects of endogenous stratification. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/COUNT/loomis.csv", + "filename": "loomis", + "name": "loomis", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The allbacks data frame gives measurements on the volume and weight of 15 books, some of which are softback (pb) and some of which are hardback (hb). Area of the hardback covers is also included. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/allbacks.csv", + "filename": "allbacks", + "name": "Measurements on a Selection of Books", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Measurements of sugar content in frosted flakes breakfast cereal. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/cerealsugar.csv", + "filename": "cerealsugar", + "name": "Percentage of Sugar in Breakfast Cereal", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A non-experimental \"control\" group, used in various studies of the effect of a labor training program, alternative to the experimental control group in nswdemo. ", + "download": "http://vincentarelbundock.github.io/Rdatasets/csv/DAAG/cps1.csv", + "filename": "cps1", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A non-experimental \"control\" group, used in various studies of the effect of a labor training program, alternative to the experimental control group in nswdemo. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/cps2.csv", + "filename": "cps2", + "name": "Labour Training Evaluation Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The dewpoint data frame has 72 rows and 3 columns. Monthly data were obtained for a number of sites (in Australia) and a number of months. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/dewpoint.csv", + "filename": "dewpoint", + "name": "Dewpoint Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The elastic1 data frame has 7 rows and 2 columns giving, for each amount by which an elastic band is stretched over the end of a ruler, the distance that the band traveled when released. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/elastic1.csv", + "filename": "elastic1", + "name": "Elastic Band Data Replicated", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The elastic2 data frame has 9 rows and 2 columns giving, for each amount by which an elastic band is stretched over the end of a ruler, the distance that the band traveled when released. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/elastic2.csv", + "filename": "elastic2", + "name": "Elastic Band Data Replicated Again", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The elasticband data frame has 7 rows and 2 columns giving, for each amount by which an elastic band is stretched over the end of a ruler, the distance that the band traveled when released. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/elasticband.csv", + "filename": "elasticband", + "name": "Elastic Band Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The frosted flakes data frame has 101 rows and 2 columns giving the sugar concentration (in percent) for 25 g samples of a cereal as measured by 2 methods – high performance liquid chromatography (a slow accurate lab method) and a quick method using the infra-analyzer 400. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/frostedflakes.csv", + "filename": "frostedflakes", + "name": "Frosted Flakes data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The modelcars data frame has 12 rows and 2 columns. The data are for an experiment in which a model car was released three times at each of four different distances up a 20 degree ramp. The experimenter recorded distances traveled from the bottom of the ramp across a concrete floor. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/modelcars.csv", + "filename": "modelcars", + "name": "Model Car Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "SASname and longname are from the SAS XPT file nass9702cor.XPT that is available from the webite noted below. The name shortname is the name used in the data frame nass9702cor, not included in this package, but available from my website that is noted below. It is also used in nassCDS, for columns that nassCDS includes. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nasshead.csv", + "filename": "nasshead", + "name": "Documentation of names of columns in nass9702cor", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data giving thickness (mm), height (cm), width (cm) and weight (g), of 12 books. Books were selected so that thickness decreased as page area increased ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/oddbooks.csv", + "filename": "oddbooks", + "name": "Measurements on 12 books", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Record of the number and type of O-ring failures prior to the tragic Challenger mission in January, 1986. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/orings.csv", + "filename": "orings", + "name": "Challenger O-rings Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The pair65 data frame has 9 rows and 2 columns. Eighteen elastic bands were divided into nine pairs, with bands of similar stretchiness placed in the same pair. One member of each pair was placed in hot water (60-65 degrees C) for four minutes, while the other was left at ambient temperature. After a wait of about ten minutes, the amounts of stretch, under a 1.35 kg weight, were recorded. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/pair65.csv", + "filename": "pair65", + "name": "Heated Elastic Bands", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This is a subset of the allbacks data frame which gives measurements on the volume and weight of 8 paperback books. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/softbacks.csv", + "filename": "softbacks", + "name": "Measurements on a Selection of Paperback Books", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Closing numbers for S and P 500 Index, Jan. 1, 1990 through early 2000. ", + "download": "http://vincentarelbundock.github.io/Rdatasets/csv/DAAG/SP500close.csv", + "filename": "SP500close", + "name": "Closing Numbers for S and P 500 Index", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Closing numbers for S and P 500 Index, Jan. 1, 1990 through early 2000. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/SP500W90.csv", + "filename": "SP500W90", + "name": "Closing Numbers for S and P 500 Index - First 100 Days of 1990", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Four x-y datasets which have the same traditional statistical properties (mean, variance, correlation, regression line, etc.), yet are quite different. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/anscombe.csv", + "filename": "anscombe", + "name": "Anscombe's Quartet of ‘Identical’ Simple Linear Regressions", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The numbers of “great” inventions and scientific discoveries in each year from 1860 to 1959. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/discoveries.csv", + "filename": "discoveries", + "name": "Yearly Numbers of Important Discoveries", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Freeny's data on quarterly revenue and explanatory variables. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/freeny.csv", + "filename": "freeny", + "name": "Freeny's Revenue Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A correlation matrix of eight physical measurements on 305 girls between ages seven and seventeen. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/Harman23.cor.csv", + "filename": "Harman23cor", + "name": "Harman Example 2.3", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Other" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data on police treatment of individuals arrested in Toronto for simple possession of small quantities of marijuana. The data are part of a larger data set featured in a series of articles in the Toronto Star newspaper. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Arrests.csv", + "filename": "Arrests", + "name": "Arrests for Marijuana Possession", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data are drawn from the 1997-2001 British Election Panel Study (BEPS). ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/BEPS.csv", + "filename": "BEPS", + "name": "British Election Panel Study", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Bfox data frame has 30 rows and 7 columns. Time-series data on Canadian women's labor-force participation, 1946–1975. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Bfox.csv", + "filename": "Bfox", + "name": "Canadian Women's Labour-Force Participation", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data are drawn from the 2011 Canadian National Election Study, including a question on banning abortion and variables relelated to the sampling design.", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/CES11.csv", + "filename": "CES11", + "name": " 2011 Canadian National Election Study, With Attitude Toward Abortion", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Chile data frame has 2700 rows and 8 columns. The data are from a national survey conducted in April and May of 1988 by FLACSO/Chile. There are some missing data. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Chile.csv", + "filename": "Chile", + "name": "Voting Intentions in the 1988 Chilean Plebiscite", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Florida data frame has 67 rows and 11 columns. Vote by county in Florida for President in the 2000 election. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Florida.csv", + "filename": "Florida", + "name": "Florida County Voting", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Freedman data frame has 110 rows and 4 columns. The observations are U. S. metropolitan areas with 1968 populations of 250,000 or more. There are some missing data. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Freedman.csv", + "filename": "Freedman", + "name": "Crowding and Crime in U. S. Metropolitan Areas", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Greene data frame has 384 rows and 7 columns. These are cases filed in 1990, in which refugee claimants rejected by the Canadian Immigration and Refugee Board asked the Federal Court of Appeal for leave to appeal the negative ruling of the Board. \n", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Greene.csv", + "filename": "Greene", + "name": "Refugee Appeals", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Hartnagel data frame has 38 rows and 7 columns. The data are an annual time-series from 1931 to 1968. There are some missing data. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Hartnagel.csv", + "filename": "Hartnagel", + "name": "Canadian Crime-Rates Time Series", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Results of nearly all stops made by the Minneapolis Police Department for the year 2017. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/MplsStops.csv", + "filename": "MplsStops", + "name": " Minneapolis Police Department 2017 Stop Data ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "This data set is originally from Rossi et al. (1980), and is used as an example in Allison (1995). The data pertain to 432 convicts who were released from Maryland state prisons in the 1970s and who were followed up for one year after release. Half the released convicts were assigned at random to an experimental treatment in which they were given financial aid; half did not receive aid. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Rossi.csv", + "filename": "Rossi", + "name": "Rossi et al.'s Criminal Recidivism Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A data frame with the percents of votes given to the republican candidate in presidential elections from 1856 to 1976. Rows represent the 50 states, and columns the 31 elections. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/votes.repub.csv", + "filename": "votes_repub", + "name": "Votes for Republican Candidate in Presidential Elections", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data of 3000 male criminals over 20 years old undergoing their sentences in the chief prisons of England and Wales. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/crimtab.csv", + "filename": "crimtab", + "name": "Student's 3000 Criminals Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Administration" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data were collected in a study of how data on various characteristics of the bloood varied with sport body size and sex of the athlete. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/DAAG/ais.csv", + "filename": "ais", + "name": "Australian athletes data set", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Year and birth, lifespan, etc, of British first class cricketers, born 1840-1960, whose handedness could be determined from information in the Who's who of cricketers. The status (alive=0, dead =1), and lifetime or lifespan, is for 1992. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/cricketer.csv", + "filename": "cricketer", + "name": "Lifespans of UK 1st class cricketers born 1840-1960", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Data were from the 2007 calendar for the Northern Ireland Mountain Running Association. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/nihills.csv", + "filename": "nihills", + "name": "Record times for Northern Ireland mountain running events", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Sport" + }, + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data consist of 4601 email items, of which 1813 items were identified as spam. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/spam7.csv", + "filename": "spam7", + "name": "Spam E-mail Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "Technology" + } ] }, { "category_name": "Physics", "subcategories": [ { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "Between May 1934 and July 1935, the National Bureau of Standards in Washington D.C. conducted a series of experiments to estimate the acceleration due to gravity, g, at Washington. Each experiment produced a number of replicate estimates of g using the same methodology. Although the basic method remained the same for all experiments, that of the reversible pendulum, there were changes in configuration. \nThe gravity data frame contains the data from all eight experiments. The grav data frame contains the data from the experiments 7 and 8. The data are expressed as deviations from 980.000 in centimetres per second squared. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/grav.csv", "filename": "grav", "name": " Acceleration Due to Gravity ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true }, { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "Between May 1934 and July 1935, the National Bureau of Standards in Washington D.C. conducted a series of experiments to estimate the acceleration due to gravity, g, at Washington. Each experiment produced a number of replicate estimates of g using the same methodology. Although the basic method remained the same for all experiments, that of the reversible pendulum, there were changes in configuration. \nThe gravity data frame contains the data from all eight experiments. The grav data frame contains the data from the experiments 7 and 8. The data are expressed as deviations from 980.000 in centimetres per second squared. ", "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/gravity.csv", "filename": "gravity", "name": "Acceleration Due to Gravity ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The toycars data frame has 27 rows and 3 columns. Observations are on the distance traveled by one of three different toy cars on a smooth surface, starting from rest at the top of a 16 inch long ramp tilted at varying angles. ", + "download": "http://vincentarelbundock.github.io/Rdatasets/csv/DAAG/toycars.csv", + "filename": "toycars", + "name": "Toy Cars Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true } ], "subcategory_name": "Mechanics" }, { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "PET film is used in electrical insulation. In this accelerated life test the failure times for 44 samples in gas insulated transformers. 4 different voltage levels were used. ", "download": "https://vincentarelbundock.github.io/Rdatasets/doc/boot/hirose.html", "filename": "hirose", "name": " Failure Time of PET Film ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true } ], "subcategory_name": "Electronics" }, { "datasets": [ { "DateTime_format": "yyyy-MM-dd", "comment_character": "#", "create_index_column": false, "description": "The tau particle is a heavy electron-like particle discovered in the 1970's by Martin Perl at the Stanford Linear Accelerator Center. Soon after its production the tau particle decays into various collections of more stable particles. About 86% of the time the decay involves just one charged particle. This rate has been measured independently 13 times. \nThe one-charged-particle event is made up of four major modes of decay as well as a collection of other events. The four main types of decay are denoted rho, pi, e and mu. These rates have been measured independently 6, 7, 14 and 19 times respectively. Due to physical constraints each experiment can only estimate the composite one-charged-particle decay rate or the rate of one of the major modes of decay. \nEach experiment consists of a major research project involving many years work. One of the goals of the experiments was to estimate the rate of decay due to events other than the four main modes of decay. These are uncertain events and so cannot themselves be observed directly. ", - "download": "vincentarelbundock.github.io/Rdatasets/csv/boot/tau.csv", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/boot/tau.csv", "filename": "tau", "name": " Tau Particle Decay Modes ", "number_format": 31, "remove_quotes": true, "separator": ",", "simplify_whitespaces": true, "skip_empty_parts": false, "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "A classical data of Michelson (but not this one with Morley) on measurements done in 1879 on the speed of light. The data consists of five experiments, each consisting of 20 consecutive ‘runs’. The response is the speed of light measurement, suitably coded (km/sec, with 299000 subtracted). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/morley.csv", + "filename": "morley", + "name": "Michelson Speed of Light Data", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true } ], "subcategory_name": "Nuclear" } ] + }, + { + "category_name": "Chemistry", + "subcategories": [ + { + "datasets": [ + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The data give the chemical composition of ancient pottery found at four sites in Great Britain. They appear in Hand, et al. (1994), and are used to illustrate MANOVA in the SAS Manual. (Suggested by Michael Friendly.) ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Pottery.csv", + "filename": "Pottery", + "name": "Chemical Composition of Pottery", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "Soil characteristics were measured on samples from three types of contours (Top, Slope, and Depression) and at four depths (0-10cm, 10-30cm, 30-60cm, and 60-90cm). The area was divided into 4 blocks, in a randomized block design. (Suggested by Michael Friendly.) ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/carData/Soils.csv", + "filename": "Soils", + "name": "Soil Compositions of Physical and Chemical Characteristics", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The pluton data frame has 45 rows and 4 columns, containing percentages of isotopic composition of 45 Plutonium batches. ", + "download": "https://vincentarelbundock.github.io/Rdatasets/csv/cluster/pluton.csv", + "filename": "pluton", + "name": "Isotopic Composition Plutonium Batches", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The ironslag data frame has 53 rows and 2 columns. Two methods for measuring the iron content in samples of slag were compared, a chemical and a magnetic method. The chemical method requires greater effort than the magnetic method. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/DAAG/ironslag.csv", + "filename": "ironslag", + "name": "Iron Content Measurements", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The BOD data frame has 6 rows and 2 columns giving the biochemical oxygen demand versus time in an evaluation of water quality. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/BOD.csv", + "filename": "BOD", + "name": " Biochemical Oxygen Demand ", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "These data are from a chemical experiment to prepare a standard curve for the determination of formaldehyde by the addition of chromatropic acid and concentrated sulphuric acid and the reading of the resulting purple color on a spectrophotometer. ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/Formaldehyde.csv", + "filename": "Formaldehyde", + "name": "Determination of Formaldehyde", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + }, + { + "DateTime_format": "yyyy-MM-dd", + "comment_character": "#", + "create_index_column": false, + "description": "The Indometh data frame has 66 rows and 3 columns of data on the pharmacokinetics of indometacin (or, older spelling, ‘indomethacin’). ", + "download": "vincentarelbundock.github.io/Rdatasets/csv/datasets/Indometh.csv", + "filename": "Indometh", + "name": "Pharmacokinetics of Indomethacin", + "number_format": 31, + "remove_quotes": true, + "separator": ",", + "simplify_whitespaces": true, + "skip_empty_parts": false, + "use_first_row_for_vectorname": true + } + ], + "subcategory_name": "General" + } + ] } ], "collection_name": "R_Datasets" }