{"id":"W1841123149","doi":"10.1080/02602938.2015.1044421","title":"Whose feedback? A multilevel analysis of student completion of end-of-term teaching evaluations","year":2015,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Respondent; Set (abstract data type); Psychology; Quality (philosophy); Quality assurance; Term (time); Higher education; Medical education; Multilevel model; Course evaluation; Mathematics education; Computer science; Medicine; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.02087735,0.0003393165,0.00102834,0.00233775,0.000936223,0.001997424,0.001572585,0.0007430412,0.002663978],"category_scores_gemma":[0.08534364,0.000278128,0.002051787,0.002535133,0.0006594807,0.001124479,0.00201611,0.00177433,0.0004418001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001873754,"about_ca_system_score_gemma":0.001908369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03324432,"about_ca_topic_score_gemma":0.03204249,"domain_scores_codex":[0.975282,0.01547657,0.00188264,0.001885774,0.003750105,0.001723001],"domain_scores_gemma":[0.9041569,0.05550199,0.01886938,0.007856843,0.01011389,0.003501023],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002893977,0.0001392583,0.9846045,0.00005595503,0.0009758554,0.00002345987,0.002577034,0.000317132,0.0001438486,0.000190134,0.0004531818,0.01023017],"study_design_scores_gemma":[0.00001397271,0.0004110002,0.995083,0.00003963386,0.0001734653,0.00001808662,0.001421193,0.00205023,0.0001849948,0.0001273737,0.0004599137,0.00001711133],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962158,0.000115166,0.001597124,0.0002155196,0.00001310112,0.0001068512,0.001039804,0.0000271951,0.000669511],"genre_scores_gemma":[0.9980082,0.00002807295,0.000816534,0.0000201207,0.000006490146,0.000124607,0.0005643633,0.00001010886,0.0004215541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9791226,"threshold_uncertainty_score":0.1104113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4085236037266901,"score_gpt":0.6050658361994158,"score_spread":0.1965422324727257,"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."}}