{"id":"W2599980125","doi":"10.1080/2331186x.2017.1304016","title":"Student evaluations of teaching are an inadequate assessment tool for evaluating faculty performance","year":2017,"lang":"en","type":"article","venue":"Cogent Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":307,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University","funders":"","keywords":"Summative assessment; Set (abstract data type); Medical education; Formative assessment; Faculty development; Psychology; Evaluation methods; Program evaluation; Course evaluation; Teaching method; Mathematics education; Higher education; Pedagogy; Computer science; Medicine; Professional development; Engineering; Political science","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01112045,0.0001081441,0.0001502142,0.0000852408,0.003648847,0.0003607655,0.0006000025,0.00006278516,0.00009002562],"category_scores_gemma":[0.006274597,0.0001132396,0.00006206943,0.00004336186,0.0001045305,0.00164437,0.00006030636,0.0001695831,0.00001116746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004206764,"about_ca_system_score_gemma":0.001751248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006408431,"about_ca_topic_score_gemma":0.0002554189,"domain_scores_codex":[0.9973636,0.0007590488,0.0003810238,0.0002788712,0.001009241,0.0002082268],"domain_scores_gemma":[0.9969403,0.0002892443,0.00131218,0.0005218993,0.000854283,0.00008216718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002423035,0.001175818,0.4458916,0.00008769307,0.00006047664,3.816361e-8,0.04085214,0.0009358563,0.001657225,0.03223612,0.00091635,0.4761624],"study_design_scores_gemma":[0.0004628144,0.0002057906,0.9583969,0.0001385582,0.0001649444,2.803475e-7,0.0225278,0.007759754,0.0002788529,0.001168616,0.008697892,0.0001977569],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845595,0.00003461592,0.001928742,0.005569698,0.001137702,0.001210329,0.00001194204,0.00003828973,0.005509125],"genre_scores_gemma":[0.9784628,0.00001911221,0.01924239,0.00008130082,0.0003517898,0.0003641565,0.00008065843,0.00001282269,0.001385026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5125054,"threshold_uncertainty_score":0.9976482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.330727264537629,"score_gpt":0.6184685834139221,"score_spread":0.2877413188762931,"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."}}