{"id":"W2599662706","doi":"","title":"PAPER: Examining Validity Evidence for Multidimensional Forced Choice Measures using Four Scoring Approaches","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Two-alternative forced choice; Item response theory; Psychology; Test (biology); Normative; Likert scale; Classical test theory; Rank (graph theory); Statistics; Psychometrics; Social psychology; Mathematics; Cognitive psychology; Clinical psychology; Developmental psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1427534,0.001387674,0.001220492,0.006759272,0.0028299,0.004894155,0.003156346,0.001937185,0.009720724],"category_scores_gemma":[0.4304318,0.0006317914,0.003368416,0.005737255,0.005482672,0.006451876,0.005244147,0.002474861,0.001423445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002862982,"about_ca_system_score_gemma":0.00300552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001443085,"about_ca_topic_score_gemma":0.001417993,"domain_scores_codex":[0.8281459,0.1040701,0.01425179,0.0121702,0.03992104,0.001440927],"domain_scores_gemma":[0.2673074,0.5939977,0.0483409,0.03926019,0.04881157,0.002282363],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002447243,0.000872754,0.7449818,0.001193209,0.001964807,0.0001569737,0.01061236,0.001399077,0.00104044,0.02703957,0.003125816,0.2051659],"study_design_scores_gemma":[0.001139726,0.004707618,0.8607566,0.003337367,0.001847093,0.00126778,0.01267448,0.03741439,0.006755143,0.04822455,0.02133365,0.0005416299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8592622,0.002609628,0.0879347,0.002729602,0.001498602,0.00283122,0.002010459,0.0002451356,0.04087846],"genre_scores_gemma":[0.9522648,0.0004962943,0.04132886,0.0006761606,0.0002810298,0.002658152,0.0008145085,0.000111196,0.001368905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8572466,"threshold_uncertainty_score":0.7549612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.690729672794958,"score_gpt":0.3971126026713275,"score_spread":0.2936170701236305,"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."}}