{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2246548,0.001864325,0.00182753,0.003200948,0.001232548,0.002957797,0.003533938,0.001897482,0.002831019],"category_scores_gemma":[0.5783927,0.0008860425,0.00210609,0.004959769,0.002387419,0.004695791,0.004801919,0.003196447,0.000942643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001626488,"about_ca_system_score_gemma":0.001925302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008502225,"about_ca_topic_score_gemma":0.0010278,"domain_scores_codex":[0.7399748,0.2243471,0.01051213,0.01098689,0.01340613,0.0007730176],"domain_scores_gemma":[0.376565,0.5199229,0.02338755,0.05294217,0.02638422,0.0007982188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00235677,0.0007740978,0.07198077,0.001138099,0.002573541,0.0002177803,0.00724459,0.04874792,0.007406957,0.03818785,0.001704613,0.8176669],"study_design_scores_gemma":[0.0008978567,0.004252087,0.07400165,0.001025165,0.001322688,0.001622566,0.003344226,0.7923597,0.03406962,0.07382856,0.01265728,0.0006185352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1001273,0.0003905313,0.8948936,0.0001794077,0.0001083418,0.0008579048,0.00007739105,0.0006670575,0.002698476],"genre_scores_gemma":[0.3569662,0.0001432705,0.6404704,0.0001430763,0.00003256529,0.00127742,0.0002353478,0.0003257669,0.0004058995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2246548,"threshold_uncertainty_score":0.9561386,"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."}}