{"id":"W2070673350","doi":"10.1177/0146621606292215","title":"Investigation of IRT-Based Equating Methods in the Presence of Outlier Common Items","year":2008,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Equating; Outlier; Statistics; Item response theory; Calibration; Comparability; Mathematics; Econometrics; Computer science; Psychometrics","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":["metaresearch"],"category_scores_codex":[0.04040952,0.0001717794,0.0005492193,0.0003424393,0.0001106472,0.00002343053,0.001315474,0.0001329161,0.00007316628],"category_scores_gemma":[0.03888406,0.00009443393,0.0001210291,0.002910648,0.0004278803,0.00004911671,0.00007648367,0.0003168237,0.000007465493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003168411,"about_ca_system_score_gemma":0.00003266718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004256998,"about_ca_topic_score_gemma":0.000004667187,"domain_scores_codex":[0.9919676,0.002857596,0.001580675,0.0005703066,0.002716125,0.0003076698],"domain_scores_gemma":[0.9716399,0.02610949,0.0009193787,0.0009425091,0.0003186446,0.00007006957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002982326,0.0006019457,0.419363,0.00003458612,0.00002823758,0.000008083509,0.003165453,0.001900379,0.2201929,0.006336234,0.002059379,0.3460116],"study_design_scores_gemma":[0.001032091,0.0003859058,0.9069838,0.00005049064,0.0000112765,0.000005960088,0.001138358,0.0012385,0.02045108,0.06812163,0.0003843038,0.0001966053],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8062878,0.0002468303,0.1744903,0.0004985931,0.0002625687,0.0006356837,0.00000221155,0.00002679538,0.01754921],"genre_scores_gemma":[0.8362443,0.000005442124,0.1632294,0.0004221488,0.00002501884,0.00006321304,7.035448e-7,0.000005161414,0.000004537842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4876208,"threshold_uncertainty_score":0.9881003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8304468687797645,"score_gpt":0.5388212625480718,"score_spread":0.2916256062316926,"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."}}