{"id":"W4365813887","doi":"10.1080/08957347.2023.2201703","title":"Multi-Group Generalizations of SIBTEST and Crossing-SIBTEST","year":2023,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Type I and type II errors; Differential item functioning; Statistics; Mathematics; Monte Carlo method; Logistic regression; Set (abstract data type); Population; Group (periodic table); Statistical power; Applied mathematics; Item response theory; Computer science; Psychometrics; Demography","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"],"consensus_categories":[],"category_scores_codex":[0.007057887,0.0001025635,0.0002019157,0.0007882515,0.0001604936,0.0001532554,0.0002666744,0.00005727429,0.00002914561],"category_scores_gemma":[0.01823118,0.00008741942,0.00002710293,0.003610788,0.0001004703,0.00009875149,0.00006686222,0.00007633861,0.00002926074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006746985,"about_ca_system_score_gemma":0.0001975211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001091461,"about_ca_topic_score_gemma":0.0001017184,"domain_scores_codex":[0.9977792,0.000128563,0.0006096356,0.000381448,0.0009000583,0.0002010751],"domain_scores_gemma":[0.9970587,0.001891373,0.0002825612,0.0003727963,0.0003295388,0.00006495764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001186769,0.000496547,0.4914772,0.00003178439,0.00001011715,2.278856e-7,0.001793361,0.0007562803,0.1121447,0.005127875,0.004949647,0.3832004],"study_design_scores_gemma":[0.0003832292,0.00002104808,0.9767169,0.00003482462,0.000007164126,9.450978e-7,0.00252461,0.001435452,0.001216855,0.01303161,0.004500809,0.0001265428],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975493,0.0005826306,0.01754891,0.0004522743,0.001038431,0.0004651044,0.000004358495,0.00007983523,0.00433544],"genre_scores_gemma":[0.9632537,0.00004917711,0.03631192,0.00009164553,0.00006309922,0.0000756052,0.000009985295,0.000009390904,0.0001355049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4852397,"threshold_uncertainty_score":0.9900387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5905972101310687,"score_gpt":0.4788309874553456,"score_spread":0.1117662226757231,"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."}}