{ "data_id": "681", "name": "hutsof99_logis", "exact_name": "hutsof99_logis", "version": 1, "version_label": null, "description": "**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nGraeme D. Hutcheson and Nick Sofroniou 1999\n\nThe Multivariate Social Scientist:\nIntroductory Statistics Using Generalized Linear Models.\n\nSAGE Publications.\n\nCopyright: Graeme D. Hutcheson & Nick Sofroniou, 1999\n\nThis software can be freely used for non-commercial purposes and can be\nfreely distributed.\n\n\nReadme file\n===========\n\nThe data sets in this directory are taken from the above book.\nThe data are presented in two formats, *.dat (ascii) and\n*.por (SPSS portable). The GLIM code and macros are provided in\nfiles *.glm and *.mac. Please read the errata file which indicates some\nminor differences between these data sets and those reported in the\nbook.\n\n\n\n\nDATA FILE SOURCE IN BOOK DESCRIPTION\n\nChapter 1\ntab1_01.* Table 1.1 Video Games and Hostility\n\nChapter 2\ntab2_01.* Table 2.1 Normal Errors\ntab2_02.* Table 2.2 Skewed Errors\ntab2_03.* Table 2.3 Curvilinearity\n\nChapter 3\ntab3_01.* Table 3.1 Two Simple Models\ntab3_05.* Table 3.5 Cost and Sound Quality\ntab3_07.* Table 3.7 Exam marks and College Offers\ntab3_11.* Table 3.11 Quality of Children's Testimonies\nAge: 5-6 = 0; 8-9 = 1\nGender: female = 0; male = 1\nLocation: 1 = home; 2 = school;\n3 = police interview\n4 = special interview\ntab3_11d.* Table 3.11 Data in Table 3.11 with indicator dummy codes\nadded\n\nChapter 4\ntab4_01.* Table 4.1 Infection Severity and Treatment Outcome\nTreatment Outcome: 0 = survived\n1 = died\ntab4_14.* Table 4.14 Infection severity, Treatment outcome and\nHospital Attended\nHospital: 1 = hospital A\n2 = hospital B\n3 = hospital C\ntab4.14d.* Table 4.14 Infection severity, Treatment outcome and\nHospital Attended including dummy codes\n\nlogis.* Child witness data: copy of\ntab3_11, but includes prosecution\nlogis_d.* Child witness data: copy of\ntab3_11d, but includes prosecution\n\nlogis.por and logis_d.por provide the data to\nobtain the parameters calculated in the book\n(pages 147 to 152). It should be noted that\nthese differ slightly to the parameters\nobtained using the data sets logis.dat and\nlogis_d.dat, as the *.dat files only record\nthe variable 'coherence' to 2 decimal places.\n\nChapter 5\n\ntab5_01.* Table 5.1 Job Satisfaction for doctors and dentists\ntab5_04.* Table 5.4 Race, Housing and Illness\ntab5_07.* Table 5.7 Dopamine and psychosis: integer scoring\ntab5_08.* Table 5.8 Dopamine and psychosis: mid-ranks scoring\ntab5_10.* Table 5.10 Treatment and Depression: integer scoring\ntab5_11.* Table 5.11 Treatment and depression: mid-ranks scoring\ntab5_13.* Table 5.13 Alcohol consumption and Libido: integer scores\ntab5_16.* Table 5.16 Alcohol consumption and libido: low vs medium\nor high\ntab5_17.* Table 5.17 Alcohol consumption and libido: medium vs high\n\n\nChapter 6\n\ntab6_11.* Table 6.11 Child witness example data set\n\nFile: ..\/data\/hutsof99\/logis.dat\n\nNote: changes from Errata.txt where not included!\n\n\nInformation about the dataset\nCLASSTYPE: numeric\nCLASSINDEX: none specific", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": "Graeme D. Hutcheson, Nick Sofroniou ", "contributor": null, "date": "2014-10-04 13:54:20", "update_comment": "set target feature", "last_update": "2014-10-07 02:26:41", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52981\/hutsof99_logis.arff", "kaggle_url": null, "default_target_attribute": "Quality", "row_id_attribute": null, "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "hutsof99_logis", "Graeme D. Hutcheson and Nick Sofroniou 1999 The Multivariate Social Scientist: Introductory Statistics Using Generalized Linear Models. SAGE Publications. Copyright: Graeme D. Hutcheson & Nick Sofroniou, 1999 This software can be freely used for non-commercial purposes and can be freely distributed. Readme file =========== The data sets in this directory are taken from the above book. The data are presented in two formats, *.dat (ascii) and *.por (SPSS portable). The GLIM code and macros are pro " ], "weight": 5 }, "qualities": { "NumberOfInstances": 70, "NumberOfFeatures": 8, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 4, "NumberOfSymbolicFeatures": 4, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 37.5, "Quartile2StdDevOfNumericAtts": 5.9446718453003715, "RandomTreeDepth1AUC": null, "Dimensionality": 0.11428571428571428, "MaxNominalAttDistinctValues": 4, "MinSkewnessOfNumericAtts": -0.28668947243223875, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxSkewnessOfNumericAtts": 0.23759060759453002, "MinStdDevOfNumericAtts": 0.8401335913685131, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.2561691322253906, "AutoCorrelation": 0.18086956521739114, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxStdDevOfNumericAtts": 25.329387019643608, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 50, "Quartile3MeansOfNumericAtts": 57.14582142857142, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 50, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanKurtosisOfNumericAtts": -0.45699669027226786, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.23641128928431349, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanMeansOfNumericAtts": 28.24235714285714, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.7531214600649951, "Quartile3StdDevOfNumericAtts": 21.757938561674464, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 2.797892857142857, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 3, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNominalAttDistinctValues": 2.5, "Quartile1SkewnessOfNumericAtts": -0.16239990646279218, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": 1, "J48.001.ErrRate": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 0.09856081524037566, "Quartile1StdDevOfNumericAtts": 0.841537819234813, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 9.514716075403216, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -0.3616994785264178, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.856574892763212, "Quartile2MeansOfNumericAtts": 24.783357142857138, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxKurtosisOfNumericAtts": -0.24801291127302383, "MinMeansOfNumericAtts": 2.794, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxMeansOfNumericAtts": 60.608714285714285, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.22167106289960567, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null }, "tags": [ { "uploader": "38960", "tag": "Biomedicine" }, { "uploader": "38960", "tag": "Education" }, { "uploader": "38960", "tag": "Sociology" }, { "uploader": "24659", "tag": "StatLib" }, { "uploader": "7210", "tag": "survival" } ], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "Quality", "index": "7", "type": "numeric", "distinct": "70", "missing": "0", "target": "1", "min": "34", "max": "83", "mean": "61", "stdev": "11" }, { "name": "Age", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Gender", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Location", "index": "2", "type": "nominal", "distinct": "4", "missing": "0", "distr": [] }, { "name": "Coherence", "index": "3", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Maturity", "index": "4", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Delay", "index": "5", "type": "numeric", "distinct": "50", "missing": "0", "min": "2", "max": "102", "mean": "47", "stdev": "25" }, { "name": "Prosecute", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }