{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.193742,0.001144131,0.00198503,0.004999162,0.003939931,0.01771523,0.003311963,0.007325368,0.003654259],"category_scores_gemma":[0.6254682,0.0008804003,0.0009986931,0.003473836,0.02289517,0.0267257,0.005237744,0.0214766,0.001569637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004770366,"about_ca_system_score_gemma":0.005709246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006890251,"about_ca_topic_score_gemma":0.008738579,"domain_scores_codex":[0.7947643,0.1707852,0.007277152,0.003380977,0.02257583,0.00121653],"domain_scores_gemma":[0.2390869,0.6810448,0.009237441,0.01668895,0.05044934,0.003492583],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004427921,0.0003713651,0.008299401,0.001177745,0.0004087556,0.0002165281,0.03084293,0.002863598,0.001038952,0.350205,0.1836162,0.4205167],"study_design_scores_gemma":[0.0001042141,0.0005760602,0.007051968,0.00274621,0.0001969624,0.0002451857,0.02503523,0.008652556,0.003142507,0.8021191,0.1496874,0.000442765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01318306,0.01104276,0.1277644,0.8226036,0.008218538,0.0002484367,0.0001093601,0.0006546106,0.01617535],"genre_scores_gemma":[0.5071436,0.0109702,0.3309605,0.1288555,0.01302642,0.0009863394,0.0001136191,0.0008528261,0.007091015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.806258,"threshold_uncertainty_score":0.9942597,"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."}}