{ "data_id": "48", "name": "tae", "exact_name": "tae", "version": 1, "version_label": "1", "description": "**Author**: \n**Source**: Unknown - \n**Please cite**: \n\n1. Title: Teaching Assistant Evaluation\n \n 2. Sources:\n (a) Collector: Wei-Yin Loh (Department of Statistics, UW-Madison)\n (b) Donor: Tjen-Sien Lim (limt@stat.wisc.edu)\n (b) Date: June 7, 1997\n \n 3. Past Usage:\n 1. Loh, W.-Y. & Shih, Y.-S. (1997). Split Selection Methods for \n Classification Trees, Statistica Sinica 7: 815-840.\n 2. Lim, T.-S., Loh, W.-Y. & Shih, Y.-S. (1999). A Comparison of\n Prediction Accuracy, Complexity, and Training Time of\n Thirty-three Old and New Classification Algorithms. Machine\n Learning. Forthcoming.\n (ftp:\/\/ftp.stat.wisc.edu\/pub\/loh\/treeprogs\/quest1.7\/mach1317.pdf or\n (http:\/\/www.stat.wisc.edu\/~limt\/mach1317.pdf)\n \n 4. Relevant Information:\n The data consist of evaluations of teaching performance over three\n regular semesters and two summer semesters of 151 teaching assistant\n (TA) assignments at the Statistics Department of the University of\n Wisconsin-Madison. The scores were divided into 3 roughly equal-sized\n categories (\"low\", \"medium\", and \"high\") to form the class variable.\n \n 5. Number of Instances: 151\n \n 6. Number of Attributes: 6 (including the class attribute)\n \n 7. Attribute Information:\n \n 1. Whether of not the TA is a native English speaker (binary)\n 1=English speaker, 2=non-English speaker\n 2. Course instructor (categorical, 25 categories)\n 3. Course (categorical, 26 categories)\n 4. Summer or regular semester (binary) 1=Summer, 2=Regular\n 5. Class size (numerical)\n 6. Class attribute (categorical) 1=Low, 2=Medium, 3=High\n \n 8. Missing Attribute Values: None\n\n Information about the dataset\n CLASSTYPE: nominal\n CLASSINDEX: last", "format": "ARFF", "uploader": "Jan van Rijn", "uploader_id": 1, "visibility": "public", "creator": "Wei-Yin Loh", "contributor": null, "date": "2014-04-06 23:22:53", "update_comment": null, "last_update": "2014-04-06 23:22:53", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/48\/dataset_48_tae.arff", "default_target_attribute": "Class_attribute", "row_id_attribute": null, "ignore_attribute": null, "runs": 2028, "suggest": { "input": [ "tae", "1. Title: Teaching Assistant Evaluation 2. Sources: (a) Collector: Wei-Yin Loh (Department of Statistics, UW-Madison) (b) Donor: Tjen-Sien Lim (limt@stat.wisc.edu) (b) Date: June 7, 1997 3. Past Usage: 1. Loh, W.-Y. & Shih, Y.-S. (1997). Split Selection Methods for Classification Trees, Statistica Sinica 7: 815-840. 2. Lim, T.-S., Loh, W.-Y. & Shih, Y.-S. (1999). A Comparison of Prediction Accuracy, Complexity, and Training Time of Thirty-three Old and New Classification Algorithms. Machine Lear " ], "weight": 5 }, "qualities": { "NumberOfInstances": 151, "NumberOfFeatures": 6, "NumberOfClasses": 3, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 3, "NumberOfSymbolicFeatures": 3, "Quartile2AttributeEntropy": 0.660678484256592, "REPTreeDepth2ErrRate": 0.4966887417218543, "CfsSubsetEval_kNN1NKappa": 0.2090617429450665, "kNN1NErrRate": 0.423841059602649, "MajorityClassPercentage": 34.437086092715234, "MeanStdDevOfNumericAtts": 8.914483709247671, "Quartile2KurtosisOfNumericAtts": -0.5013662823748297, "REPTreeDepth2Kappa": 0.25684100006562116, "ClassEntropy": 1.5845209168501238, "kNN1NKappa": 0.36366629354052804, "MajorityClassSize": 52, "MinAttributeEntropy": 0.6156105340978517, "Quartile2MeansOfNumericAtts": 13.642384105960266, "REPTreeDepth3AUC": 0.6291665298201031, "DecisionStumpAUC": 0.5817722792925962, "MaxAttributeEntropy": 0.7057464344153325, "MinKurtosisOfNumericAtts": -1.154209095385458, "Quartile2MutualInformation": 0.058865391129104994, "REPTreeDepth3ErrRate": 0.4966887417218543, "DecisionStumpErrRate": 0.609271523178808, "MaxKurtosisOfNumericAtts": -0.34747425530200804, "MinMeansOfNumericAtts": 8.105960264900663, "Quartile2SkewnessOfNumericAtts": 0.49830596469803967, "REPTreeDepth3Kappa": 0.25684100006562116, "DecisionStumpKappa": 0.09398030391965041, "MaxMeansOfNumericAtts": 27.86754966887417, "MinMutualInformation": 0.05571548973719, "PercentageOfBinaryFeatures": 33.33333333333333, "Quartile2StdDevOfNumericAtts": 7.02391374081506, "RandomTreeDepth1AUC": 0.713528939571012, "Dimensionality": 0.039735099337748346, "MaxMutualInformation": 0.06201529252102, "MinNominalAttDistinctValues": 2, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 0.7057464344153325, "RandomTreeDepth1ErrRate": 0.3973509933774834, "EquivalentNumberOfAtts": 26.917699627186956, "MaxNominalAttDistinctValues": 3, "MinSkewnessOfNumericAtts": -0.008312804753781999, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.34747425530200804, "AutoCorrelation": 0.9266666666666666, "RandomTreeDepth1Kappa": 0.40386893012238445, "J48.00001.AUC": 0.6847997616278962, "MaxSkewnessOfNumericAtts": 0.8701667338818008, "MinStdDevOfNumericAtts": 6.825778950284407, "PercentageOfNumericFeatures": 50, "Quartile3MeansOfNumericAtts": 27.86754966887417, "CfsSubsetEval_DecisionStumpAUC": 0.6071952540014423, "RandomTreeDepth2AUC": 0.713528939571012, "J48.00001.ErrRate": 0.46357615894039733, "MaxStdDevOfNumericAtts": 12.893758436643546, "MinorityClassPercentage": 32.450331125827816, "PercentageOfSymbolicFeatures": 50, "Quartile3MutualInformation": 0.06201529252102, "CfsSubsetEval_DecisionStumpErrRate": 0.5298013245033113, "RandomTreeDepth2ErrRate": 0.3973509933774834, "J48.00001.Kappa": 0.3051081454210768, "MeanAttributeEntropy": 0.660678484256592, "MinorityClassSize": 49, "Quartile1AttributeEntropy": 0.6156105340978517, "Quartile3SkewnessOfNumericAtts": 0.8701667338818008, "CfsSubsetEval_DecisionStumpKappa": 0.2090617429450665, "RandomTreeDepth2Kappa": 0.40386893012238445, "J48.0001.AUC": 0.6847997616278962, "MeanKurtosisOfNumericAtts": -0.6676832110207652, "NaiveBayesAUC": 0.6940981301090764, "Quartile1KurtosisOfNumericAtts": -1.154209095385458, "Quartile3StdDevOfNumericAtts": 12.893758436643546, "CfsSubsetEval_NaiveBayesAUC": 0.6071952540014423, "RandomTreeDepth3AUC": 0.713528939571012, "J48.0001.ErrRate": 0.46357615894039733, "MeanMeansOfNumericAtts": 16.538631346578367, "NaiveBayesErrRate": 0.44370860927152317, "Quartile1MeansOfNumericAtts": 8.105960264900663, "REPTreeDepth1AUC": 0.6291665298201031, "CfsSubsetEval_NaiveBayesErrRate": 0.5298013245033113, "RandomTreeDepth3ErrRate": 0.3973509933774834, "J48.0001.Kappa": 0.3051081454210768, "MeanMutualInformation": 0.058865391129104994, "NaiveBayesKappa": 0.3364161091433818, "Quartile1MutualInformation": 0.05571548973719, "REPTreeDepth1ErrRate": 0.4966887417218543, "CfsSubsetEval_NaiveBayesKappa": 0.2090617429450665, "RandomTreeDepth3Kappa": 0.40386893012238445, "J48.001.AUC": 0.6847997616278962, "MeanNoiseToSignalRatio": 10.223547004173913, "NumberOfBinaryFeatures": 2, "Quartile1SkewnessOfNumericAtts": -0.008312804753781999, "REPTreeDepth1Kappa": 0.25684100006562116, "CfsSubsetEval_kNN1NAUC": 0.6071952540014423, "StdvNominalAttDistinctValues": 0.5773502691896258, "J48.001.ErrRate": 0.46357615894039733, "MeanNominalAttDistinctValues": 2.3333333333333335, "Quartile1StdDevOfNumericAtts": 6.825778950284407, "REPTreeDepth2AUC": 0.6291665298201031, "CfsSubsetEval_kNN1NErrRate": 0.5298013245033113, "kNN1NAUC": 0.697331488115699, "J48.001.Kappa": 0.3051081454210768, "MeanSkewnessOfNumericAtts": 0.45338663127535284 }, "tags": [ { "uploader": "38960", "tag": "Education" }, { "uploader": "38960", "tag": "Statistics" }, { "uploader": "2", "tag": "study_1" }, { "uploader": "3886", "tag": "study_123" }, { "uploader": "1", "tag": "study_41" }, { "uploader": "64", "tag": "study_50" }, { "uploader": "64", "tag": "study_52" }, { "uploader": "64", "tag": "study_7" }, { "uploader": "4209", "tag": "study_88" }, { "uploader": "1", "tag": "uci" } ], "features": [ { "name": "Class_attribute", "index": "5", "type": "nominal", "distinct": "3", "missing": "0", "target": "1", "distr": [ [ "1", "2", "3" ], [ [ "49", "0", "0" ], [ "0", "50", "0" ], [ "0", "0", "52" ] ] ] }, { "name": "Whether_of_not_the_TA_is_a_native_English_speaker", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "5", "6", "18" ], [ "44", "44", "34" ] ] ] }, { "name": "Course_instructor", "index": "1", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "25", "mean": "14", "stdev": "7" }, { "name": "Course", "index": "2", "type": "numeric", "distinct": "26", "missing": "0", "min": "1", "max": "26", "mean": "8", "stdev": "7" }, { "name": "Summer_or_regular_semester", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "2", "6", "15" ], [ "47", "44", "37" ] ] ] }, { "name": "Class_size", "index": "4", "type": "numeric", "distinct": "46", "missing": "0", "min": "3", "max": "66", "mean": "28", "stdev": "13" } ], "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 }