{"id":"W1995348618","doi":"10.1080/00220970109599488","title":"Minimizing the Influence of Item Parameter Estimation Errors in Test Development: A Comparison of Three Selection Procedures","year":2001,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Item response theory; Selection (genetic algorithm); Statistics; Computerized adaptive testing; Function (biology); Test (biology); Range (aeronautics); Estimation; Mathematics; Equating; Estimation theory; Computer science; Artificial intelligence; Psychometrics; Rasch model; 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":[0.003755042,0.00008281849,0.0002306184,0.0003852775,0.0001105562,0.00003181079,0.0004805143,0.00003482449,0.00002231737],"category_scores_gemma":[0.03782456,0.00004353284,0.00004400331,0.001463072,0.00009711525,0.0003098521,0.00003873824,0.0001457854,0.000001337098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007958028,"about_ca_system_score_gemma":0.0003173279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008778492,"about_ca_topic_score_gemma":0.00003300706,"domain_scores_codex":[0.997765,0.0002551066,0.001138072,0.00009294821,0.0006406751,0.0001081882],"domain_scores_gemma":[0.9864438,0.01138931,0.001637217,0.00015592,0.0003453972,0.00002836707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001770085,0.0006823575,0.8139916,0.00001063137,0.00001560509,1.316129e-7,0.02056272,0.01338618,0.09219782,0.00004670755,0.0002468313,0.05868241],"study_design_scores_gemma":[0.0002007714,0.0002210539,0.8806845,0.0001538636,0.00001039607,0.00006373604,0.02242388,0.004833436,0.08958915,0.001712058,0.00004838049,0.00005876478],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964889,0.001077691,0.001743522,0.000199649,0.0001921193,0.0001552992,1.618069e-7,0.000002744531,0.0001399602],"genre_scores_gemma":[0.9768209,0.00001059103,0.02308315,0.00003350327,0.00002807495,0.00000554997,2.343347e-7,0.000003962736,0.0000140169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06669291,"threshold_uncertainty_score":0.9702802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2827474909716795,"score_gpt":0.4893092776194928,"score_spread":0.2065617866478133,"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."}}