{"id":"W2978741138","doi":"10.1177/0013164419878861","title":"A Propensity Score Method for Investigating Differential Item Functioning in Performance Assessment","year":2019,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Propensity score matching; Differential item functioning; Matching (statistics); Context (archaeology); Psychology; Proxy (statistics); Language proficiency; Aptitude; Set (abstract data type); Test (biology); Computer science; Psychometrics; Statistics; Natural language processing; Cognitive psychology; Item response theory; Machine learning; Developmental psychology; Mathematics; Mathematics education","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":[0.008982325,0.0001485489,0.0003112261,0.0002267241,0.0001881225,0.0001519592,0.0002814519,0.00007723107,0.0005146002],"category_scores_gemma":[0.01574548,0.00009559405,0.00006526914,0.0006900351,0.00004837473,0.0001399267,0.00007072685,0.0002276572,0.00001778627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008667899,"about_ca_system_score_gemma":0.00007842275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001306476,"about_ca_topic_score_gemma":0.000004499461,"domain_scores_codex":[0.996895,0.0004550871,0.0005988905,0.000694811,0.001083199,0.0002730183],"domain_scores_gemma":[0.9924827,0.006486253,0.0002528046,0.0002640201,0.0003992723,0.0001149162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004068296,0.0001985318,0.8944857,0.00001800246,0.000008313528,8.898317e-8,0.00008055066,0.0000769228,0.002288225,0.001693938,0.0005837455,0.1005254],"study_design_scores_gemma":[0.0005637436,0.0003063206,0.9732747,0.00006251464,0.000004813251,0.000007357346,0.0001216014,0.003625702,0.00004581411,0.02100385,0.0008487372,0.0001348144],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962943,0.00009228509,0.02887598,0.002306052,0.001433437,0.0006194682,0.000002335923,0.0000162645,0.0037112],"genre_scores_gemma":[0.9139819,0.000005432166,0.08498016,0.000394821,0.0001832243,0.0001279417,0.000003558736,0.000005118826,0.0003179004],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1003906,"threshold_uncertainty_score":0.9925453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7918302834411759,"score_gpt":0.5152538123684256,"score_spread":0.2765764710727503,"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."}}