{"id":"W1763331641","doi":"10.1177/0013164415584576","title":"It Might Not Make a Big DIF","year":2015,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Differential item functioning; Item response theory; Statistics; Polytomous Rasch model; Computer science; Monte Carlo method; Econometrics; Type I and type II errors; Statistical hypothesis testing; Machine learning; Data mining; Artificial intelligence; Psychometrics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0101387,0.0001489979,0.0002405611,0.0002087265,0.0001397812,0.0001667443,0.000480879,0.00008620465,0.0005668987],"category_scores_gemma":[0.05947007,0.00008797546,0.00007200234,0.0008806389,0.0001222944,0.0000404057,0.00007949272,0.0001640133,0.0002546447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005420615,"about_ca_system_score_gemma":0.00008421837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001346569,"about_ca_topic_score_gemma":0.00001142225,"domain_scores_codex":[0.9958932,0.000466154,0.000541566,0.0006236774,0.00219505,0.0002803024],"domain_scores_gemma":[0.9942334,0.00408691,0.0001782622,0.000395327,0.0007164464,0.0003896648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001459428,0.000893685,0.06984503,0.000003635477,0.00002580343,0.000003526481,0.0005898251,0.000008374251,0.0004786453,0.006006123,0.1942538,0.7277456],"study_design_scores_gemma":[0.0004484912,0.0002373363,0.6071104,0.00001168114,0.000005832416,0.00003237068,0.0003834005,0.00001569859,0.0000282667,0.1191553,0.2724169,0.0001543805],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5929533,0.002606433,0.00848812,0.1696946,0.009603234,0.0004496373,0.00001708687,0.00008240417,0.2161052],"genre_scores_gemma":[0.9806212,0.00002262595,0.01148,0.004778861,0.0007407291,0.00004151489,0.000001946491,0.000005069896,0.002308026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7275912,"threshold_uncertainty_score":0.9484524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9118226372485674,"score_gpt":0.5444501445426981,"score_spread":0.3673724927058692,"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."}}