{"id":"W3099333586","doi":"10.3390/educsci10110324","title":"The Effect of Person Misfit on Item Parameter Estimation and Classification Accuracy: A Simulation Study","year":2020,"lang":"en","type":"article","venue":"Education Sciences","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Saskatchewan","funders":"","keywords":"Test (biology); Psychology; Statistics; Estimation; Item response theory; Computer science; Social psychology; Econometrics; Cognitive psychology; Psychometrics; Clinical psychology; Mathematics; Engineering","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":[0.006740898,0.00009932807,0.0001754677,0.000219955,0.0005173433,0.0004332656,0.0005085192,0.00003167852,0.00002199743],"category_scores_gemma":[0.2985781,0.00005211027,0.00004036871,0.002317264,0.0002178727,0.0003594327,0.00003490511,0.00008475564,0.00002181751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001642459,"about_ca_system_score_gemma":0.00008809756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000176369,"about_ca_topic_score_gemma":0.000001621801,"domain_scores_codex":[0.9969527,0.0009716599,0.0004353019,0.0004600121,0.001051059,0.0001292529],"domain_scores_gemma":[0.856896,0.1418536,0.000641434,0.0003170131,0.0002045456,0.00008733194],"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":[0.00003462051,0.00003806134,0.2168879,0.000004244027,0.000003789811,4.172173e-8,0.002315519,0.002712354,0.0001612708,0.0002325089,0.0004123484,0.7771974],"study_design_scores_gemma":[0.0001684128,0.001247725,0.6049054,0.00001470974,0.00001078848,5.264783e-7,0.01037521,0.3811333,0.0002256213,0.001430388,0.000415614,0.00007232526],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894332,0.0001724515,0.004358374,0.003951939,0.0004587485,0.0005281686,9.110266e-7,0.00002267871,0.001073479],"genre_scores_gemma":[0.9974755,0.000004206151,0.002265858,0.0001114199,0.0000558948,0.00002970032,5.871992e-7,0.000002949705,0.00005389174],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7771251,"threshold_uncertainty_score":0.7073303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6689828634516667,"score_gpt":0.5662955670270043,"score_spread":0.1026872964246623,"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."}}