{"id":"W2108183586","doi":"10.1093/her/cyl053","title":"Improving measurement in health education and health behavior research using item response modeling: comparison with the classical test theory approach","year":2006,"lang":"en","type":"article","venue":"Health Education Research","topic":"Motivation and Self-Concept in Sports","field":"Psychology","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Public Health Service; University of British Columbia","keywords":"Classical test theory; Item response theory; Reliability (semiconductor); Test theory; Test (biology); Scale (ratio); Computer science; Structural equation modeling; Psychometrics; Psychology; Management science; Applied psychology; Machine learning; Clinical psychology; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.05427972,0.0002279988,0.0004247405,0.001151552,0.001672879,0.0001868554,0.0003477961,0.0001536622,0.0000901788],"category_scores_gemma":[0.0006062491,0.0001807314,0.00003281542,0.001815673,0.000410386,0.0001440768,0.0000816555,0.00189251,0.00001560966],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003435588,"about_ca_system_score_gemma":0.02194836,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03414836,"about_ca_topic_score_gemma":0.002078713,"domain_scores_codex":[0.9844915,0.00974877,0.001218121,0.0009669823,0.002082824,0.001491792],"domain_scores_gemma":[0.9956729,0.001286569,0.0003953163,0.0008368688,0.001283653,0.0005246573],"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":[0.001945986,0.02309779,0.3258206,0.001349271,0.00002225294,0.000002502141,0.07948622,0.0006729263,0.000111973,0.05665451,0.1243307,0.3865053],"study_design_scores_gemma":[0.001793749,0.002227206,0.665369,0.0008026321,0.000007227241,0.00009333358,0.2767436,0.01269225,0.000007969927,0.00095871,0.03879514,0.0005091943],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8666277,0.01058314,0.004904474,0.1083357,0.0005621146,0.00686282,0.000009090134,0.00008527474,0.00202969],"genre_scores_gemma":[0.9917529,0.00005529472,0.00249801,0.001542955,0.0003836033,0.001448502,0.00006221706,0.00005723097,0.002199237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3859961,"threshold_uncertainty_score":0.9996268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4132918425751012,"score_gpt":0.5390829817823746,"score_spread":0.1257911392072734,"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."}}