{"id":"W2896763700","doi":"10.1007/s11336-018-9639-4","title":"Optimal Scores: An Alternative to Parametric Item Response Theory and Sum Scores","year":2018,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Vetenskapsrådet","keywords":"Item response theory; Nonparametric statistics; Parametric statistics; Test theory; Mathematics; Statistics; Econometrics; Psychometrics; Classical test theory; Test (biology); Computer science","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","metaepi_narrow","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03639999,0.0003839681,0.0006766973,0.008647184,0.0004456012,0.0008426222,0.00196906,0.0001674787,0.0007237399],"category_scores_gemma":[0.5033298,0.0002800286,0.0001402314,0.02320954,0.0005536353,0.0006054035,0.0004385756,0.0003208459,0.0005420907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006974187,"about_ca_system_score_gemma":0.00007097983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000059462,"about_ca_topic_score_gemma":0.00001117445,"domain_scores_codex":[0.9910485,0.003552785,0.001023689,0.001632746,0.001914678,0.0008276216],"domain_scores_gemma":[0.8328592,0.1630266,0.0005153831,0.001820857,0.000930744,0.0008471428],"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":[0.009223661,0.0003285241,0.3259622,0.000007850977,0.00009479896,0.00003236889,0.002828277,0.00007772292,0.001445055,0.00409485,0.01079436,0.6451103],"study_design_scores_gemma":[0.001222978,0.003511401,0.9312977,0.00005253719,0.00002154664,0.00005569799,0.002176518,0.0008608119,0.001695353,0.03680999,0.0216755,0.0006199535],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9363317,0.0009565077,0.05726595,0.0004128214,0.002010612,0.0004283937,0.0000381209,0.0001430054,0.002412916],"genre_scores_gemma":[0.9283056,0.00006801946,0.068743,0.0008908428,0.0006006051,0.00003006096,0.000001535346,0.00003786016,0.001322465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6444904,"threshold_uncertainty_score":0.9999652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3554798528631857,"score_gpt":0.4949946834971933,"score_spread":0.1395148306340077,"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."}}