{"id":"W2590325518","doi":"10.1177/0146621617692079","title":"Plausible-Value Imputation Statistics for Detecting Item Misfit","year":2017,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Statistics; Statistic; Item response theory; Trait; Imputation (statistics); Econometrics; Parametric statistics; Test statistic; Mathematics; Statistical hypothesis testing; Differential item functioning; Latent variable model; Item analysis; Null hypothesis; Latent variable; Computer science; Psychometrics; Missing data","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":[0.01610793,0.0002600699,0.0004754849,0.0002100711,0.00124109,0.0007584816,0.001541329,0.0001893871,0.0001950488],"category_scores_gemma":[0.1290434,0.0001809172,0.000134881,0.0003623985,0.0001486179,0.0001094695,0.000170104,0.0002543013,0.0001112662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009325043,"about_ca_system_score_gemma":0.00002699206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000131765,"about_ca_topic_score_gemma":0.00000909864,"domain_scores_codex":[0.9950816,0.0002170428,0.0009786108,0.001046965,0.00209821,0.0005775632],"domain_scores_gemma":[0.985225,0.01175572,0.001067722,0.001118193,0.0006314766,0.0002019258],"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":[0.0002355108,0.0001829769,0.007813961,0.00001256759,0.00003781842,0.000003657065,0.00007877905,0.0002076964,0.007391111,0.02795454,0.007716538,0.9483649],"study_design_scores_gemma":[0.002579736,0.0006044953,0.5173778,0.00003169721,0.00004611964,0.00001281758,0.0004023937,0.004068144,0.001857552,0.4591814,0.01328402,0.0005537791],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1014713,0.00007272288,0.8705021,0.0005109027,0.001380229,0.0008912444,0.00003228162,0.0001147611,0.02502454],"genre_scores_gemma":[0.727478,0.000004541742,0.2717344,0.0003370214,0.0002237605,0.0001373658,0.000001890002,0.00001432324,0.00006871617],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9478111,"threshold_uncertainty_score":0.954559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.72207883373125,"score_gpt":0.5322352636234017,"score_spread":0.1898435701078484,"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."}}