{"id":"W3162676432","doi":"10.1177/00131644211014261","title":"On the Performance of Semi- and Nonparametric Item Response Functions in Computer Adaptive Tests","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computerized adaptive testing; Nonparametric statistics; Item response theory; Monotonic function; Parametric statistics; Selection (genetic algorithm); Statistics; Smoothing; Polynomial; Kernel (algebra); Mathematics; Function (biology); Differential item functioning; Sample (material); Computer science; Econometrics; Psychometrics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006843746,0.00008755823,0.0001663922,0.0002377645,0.0001157415,0.0000461871,0.0001590108,0.00004705945,0.0002884709],"category_scores_gemma":[0.04094793,0.0000471245,0.00003251239,0.001703886,0.0001147859,0.00004212448,0.00005201906,0.0001662937,0.0000140205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002792421,"about_ca_system_score_gemma":0.00005468832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003059585,"about_ca_topic_score_gemma":0.000002080316,"domain_scores_codex":[0.997507,0.0008437622,0.0003647408,0.0003788627,0.0007762909,0.0001293835],"domain_scores_gemma":[0.9639496,0.03525796,0.0001244649,0.0002380391,0.0003699793,0.00005997715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001129139,0.001793348,0.7719322,0.00001011942,0.00003712654,0.000004289255,0.0004903547,0.0004876527,0.001899011,0.007698092,0.01230872,0.2022099],"study_design_scores_gemma":[0.0001961106,0.0004682621,0.9856955,0.0000345504,0.000002570984,0.00001843871,0.0001719621,0.0006119396,0.00005681023,0.01229231,0.000391564,0.00006002391],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896255,0.0006333599,0.0009820742,0.006915492,0.0004413631,0.0001077567,0.000003852081,0.00000440745,0.001286197],"genre_scores_gemma":[0.9945742,0.00003106523,0.004560649,0.0005937269,0.0000579684,0.00002069533,5.027928e-7,0.000001992055,0.0001591387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2137633,"threshold_uncertainty_score":0.9671306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.622595515931154,"score_gpt":0.4554608671959295,"score_spread":0.1671346487352245,"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."}}