{"id":"W1990233393","doi":"10.1002/ir.6","title":"Improving Judgments About Teaching Effectiveness: How to Lie Without Statistics","year":2001,"lang":"en","type":"article","venue":"New Directions for Institutional Research","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Statistical analysis; Mathematics education; Psychology; Research methodology; Higher education; Computer science; Management science; Applied psychology; Statistics; Sociology; Political science; Mathematics; Economics; Law","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01182863,0.0001285469,0.0001565309,0.00052756,0.006397911,0.0005859007,0.000393314,0.0001113193,0.0001265191],"category_scores_gemma":[0.03709957,0.0001368234,0.00006700742,0.0006555343,0.0003205197,0.0009882086,0.00008377267,0.0006645216,0.0001706086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001274001,"about_ca_system_score_gemma":0.002350895,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02097634,"about_ca_topic_score_gemma":0.009914984,"domain_scores_codex":[0.9956236,0.00139515,0.0001991515,0.0004427426,0.00172015,0.0006192153],"domain_scores_gemma":[0.9950862,0.003363056,0.00008619908,0.0002239,0.0008424412,0.0003981811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002896339,0.0003058574,0.01177612,0.00004954756,0.00008396906,0.00000609273,0.003202415,0.0008328091,0.001787856,0.6365461,0.02468198,0.3204376],"study_design_scores_gemma":[0.00056912,0.0001521093,0.01292682,0.00009733282,0.00002268996,0.000004949714,0.0008452155,0.0005105894,0.0001267517,0.006435112,0.9781266,0.0001826566],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.117333,0.0002930672,0.695275,0.02631611,0.003057344,0.004144834,0.0001809766,0.0004971546,0.1529025],"genre_scores_gemma":[0.9040943,0.00009454931,0.05847585,0.0001421534,0.001476199,0.0005054969,0.00005269219,0.00002838092,0.03513033],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9534447,"threshold_uncertainty_score":0.9948956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2853376824773551,"score_gpt":0.5458200586009814,"score_spread":0.2604823761236262,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}