{"id":"W291597054","doi":"10.5430/ijhe.v4n2p116","title":"The Tail Wagging the Dog; An Overdue Examination of Student Teaching Evaluations","year":2015,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Class (philosophy); Class size; Psychology; Test (biology); Set (abstract data type); Variance (accounting); Sample size determination; Statistics; Mathematics; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01601336,0.0002127524,0.0003099204,0.002080941,0.001263258,0.002633295,0.0008245619,0.0006849503,0.003627616],"category_scores_gemma":[0.08770151,0.0001506391,0.0004100779,0.002182438,0.002175986,0.003964518,0.002210764,0.001697401,0.0007422963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007868598,"about_ca_system_score_gemma":0.001553258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002868899,"about_ca_topic_score_gemma":0.005352075,"domain_scores_codex":[0.9889899,0.00470389,0.0004786209,0.000919953,0.004442698,0.0004648421],"domain_scores_gemma":[0.898607,0.04643614,0.02294316,0.01270232,0.01528235,0.00402906],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001779059,0.0001933899,0.8588649,0.00008552406,0.0001334426,0.00009266566,0.00637026,0.0002032738,0.0003569942,0.002301322,0.006483126,0.1247372],"study_design_scores_gemma":[0.000006928071,0.0004415862,0.981077,0.0001240065,0.00003547604,0.000204022,0.007546016,0.0009166054,0.0005326019,0.001445309,0.007645434,0.00002492987],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9712344,0.001615653,0.002866811,0.005414347,0.0002171864,0.00005509965,0.0003626962,0.00008340192,0.01815039],"genre_scores_gemma":[0.9973024,0.0002141631,0.0003755117,0.0004264371,0.00009830631,0.00001503414,0.0001083179,0.00003176081,0.001427984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9839866,"threshold_uncertainty_score":0.08468783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1634833105387061,"score_gpt":0.5496602999909036,"score_spread":0.3861769894521975,"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."}}