{"id":"W1995874702","doi":"10.1080/13803611.2014.997915","title":"What response rates are needed to make reliable inferences from student evaluations of teaching?","year":2014,"lang":"en","type":"article","venue":"Educational Research and Evaluation","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Set (abstract data type); Range (aeronautics); Statistics; Confidence interval; Stability (learning theory); Psychology; Econometrics; Computer science; Mathematics; Engineering; Machine learning","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":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06037384,0.0001076211,0.0001664121,0.000472268,0.001422941,0.0006376741,0.0003798661,0.00008898683,0.001799176],"category_scores_gemma":[0.08054115,0.0001068775,0.00003137282,0.0004978644,0.0002789024,0.001083772,0.0001018285,0.0003412331,0.0002034729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003554278,"about_ca_system_score_gemma":0.002233589,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007677795,"about_ca_topic_score_gemma":0.004638789,"domain_scores_codex":[0.9862183,0.00859986,0.0004041464,0.0004076834,0.004039878,0.0003300765],"domain_scores_gemma":[0.9820212,0.01421815,0.0002566345,0.0003213306,0.002915258,0.0002673909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001922328,0.002671622,0.2344193,0.00005999624,0.0002410927,2.300689e-7,0.3396611,0.003256903,0.009580683,0.1698703,0.1300956,0.1082209],"study_design_scores_gemma":[0.0006066111,0.0004015348,0.7075664,0.000285538,0.00005168014,2.310838e-7,0.1255289,0.002288506,0.000366542,0.1054463,0.05725489,0.0002027877],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8305631,0.0004047102,0.000061527,0.1630583,0.0005797557,0.0007831887,0.000006758305,0.00001396738,0.004528666],"genre_scores_gemma":[0.9920956,0.0001551477,0.002171646,0.0004046936,0.0005144461,0.0003080333,0.00006598508,0.00001057199,0.004273884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4731472,"threshold_uncertainty_score":0.9998771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3841725397005639,"score_gpt":0.6224553468616918,"score_spread":0.2382828071611279,"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."}}