{"id":"W2005743601","doi":"10.1037/a0024221","title":"Use of student ratings to benchmark universities: Multilevel modeling of responses to the Australian Course Experience Questionnaire (CEQ).","year":2011,"lang":"en","type":"article","venue":"Journal of Educational Psychology","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Economic and Social Research Council","keywords":"Psychology; Multilevel model; Course (navigation); Mathematics education; Benchmark (surveying); Medical education; Applied psychology; Course evaluation; Higher education; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.002165121,0.00006984955,0.00015017,0.0001925526,0.0002061893,0.00002009308,0.0005255419,0.00005353189,0.0006196273],"category_scores_gemma":[0.002153805,0.0000581675,0.00006242506,0.0002008186,0.0001899156,0.0005090697,0.00003131256,0.0001642243,0.000008595643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001083924,"about_ca_system_score_gemma":0.0009073135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001394229,"about_ca_topic_score_gemma":0.0002462814,"domain_scores_codex":[0.9980359,0.0006997575,0.0004865727,0.0001200308,0.0005269902,0.0001307168],"domain_scores_gemma":[0.9973889,0.0006790712,0.0006423644,0.0001677909,0.0009928476,0.0001290473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0007934514,0.001283766,0.1501183,0.00000982308,0.0001286161,0.000002376649,0.7863956,0.006664653,0.000964215,0.03134092,0.02098943,0.001308871],"study_design_scores_gemma":[0.0002864366,0.0004916473,0.8404267,0.0002007905,0.0000683929,0.00001870981,0.1471802,0.0001012641,0.0000747145,0.001311275,0.009696101,0.0001437787],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9456625,0.00003839349,0.0009026667,0.05137077,0.001028901,0.0001426116,0.000004954904,0.000002356382,0.0008468602],"genre_scores_gemma":[0.9855038,0.00001648505,0.01213206,0.0007155733,0.000174793,0.000004119527,4.121893e-7,0.000004559332,0.001448208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6903084,"threshold_uncertainty_score":0.6784484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3894798957291222,"score_gpt":0.5591843961155842,"score_spread":0.1697045003864621,"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."}}