{"id":"W1887917947","doi":"10.47678/cjhe.v35i2.183500","title":"The Utility of Student Ratings of Instruction for Students, Faculty, and Administrators: A \"Consequential Validity\" Study","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Higher education; Medical education; Quality (philosophy); Merit pay; Mathematics education; Medicine; Incentive; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0501954,0.0002720379,0.0004566634,0.002532594,0.0009464014,0.001842834,0.0008680939,0.0005170989,0.0006578126],"category_scores_gemma":[0.2733352,0.0002058056,0.0008130841,0.001666426,0.002357989,0.001219356,0.001424257,0.001147015,0.0001440224],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001869642,"about_ca_system_score_gemma":0.002024601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01038588,"about_ca_topic_score_gemma":0.01277371,"domain_scores_codex":[0.9487177,0.03137818,0.002927366,0.001587528,0.01431302,0.001076287],"domain_scores_gemma":[0.5816725,0.310104,0.04510916,0.01793884,0.04090714,0.004268395],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004696179,0.0002368566,0.9614993,0.00007169035,0.0002278178,0.00004124171,0.007166044,0.0003124183,0.0004328878,0.0004944019,0.0002514885,0.02879625],"study_design_scores_gemma":[0.00004032266,0.0009380522,0.9903736,0.0000669431,0.00006821338,0.0001250796,0.003176119,0.002623019,0.001053003,0.0005815704,0.0009082805,0.00004589529],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955093,0.0001270825,0.001651561,0.000108064,0.00001938345,0.0000811713,0.00007602538,0.000009011976,0.002418613],"genre_scores_gemma":[0.9991264,0.00004428799,0.0005176105,0.00002990663,0.00001602911,0.00002862348,0.00008853211,0.000003974558,0.0001445936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9981304,"threshold_uncertainty_score":0.2654618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1943694772100051,"score_gpt":0.52518544487511,"score_spread":0.3308159676651049,"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."}}