{"id":"W1976267793","doi":"10.1177/0013164403258444","title":"Gender and Language Differences on the Test of Workplace Essential Skills: Using Overall Mean Scores and Item-Level Differential Item Functioning Analyses","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Teacher Professional Development and Motivation","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Differential item functioning; Numeracy; Test (biology); Reading (process); Developmental psychology; Item response theory; Psychometrics; Literacy; Pedagogy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002854484,0.0004525888,0.000333194,0.001560685,0.0003756319,0.0005532593,0.0003867705,0.0002414095,0.001934926],"category_scores_gemma":[0.007069681,0.0001726975,0.0005170672,0.0006934306,0.0005575316,0.000542331,0.0005876603,0.0003645165,0.0002853897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004005227,"about_ca_system_score_gemma":0.0006198068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01639037,"about_ca_topic_score_gemma":0.02783994,"domain_scores_codex":[0.9986639,0.0003275569,0.0001187273,0.0002414072,0.0004145562,0.0002338788],"domain_scores_gemma":[0.9975052,0.001082667,0.0004333903,0.0001758208,0.0005466083,0.0002561792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001370115,0.00004852591,0.9910926,0.000008997596,0.000048069,0.00006532903,0.0007666841,0.0000317807,0.001246347,0.00005854029,0.0001007353,0.006395286],"study_design_scores_gemma":[0.000005216545,0.0001196187,0.9984755,0.000004021228,0.00002008642,0.00009297791,0.0004769064,0.0001623134,0.0003778168,0.00007313387,0.0001878356,0.000004493222],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983709,0.00005618246,0.0003369418,0.00003162609,0.000007055806,0.00002129483,0.0002688466,0.000004213576,0.0009029852],"genre_scores_gemma":[0.9985117,0.00002748959,0.0005623043,0.00001555639,0.000006005335,0.00002843772,0.0003778635,0.000004788241,0.0004658349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01639037,"threshold_uncertainty_score":0.03258991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2966988669348659,"score_gpt":0.4094511445808479,"score_spread":0.112752277645982,"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."}}