{"id":"W2897165533","doi":"10.3389/fpsyg.2018.01875","title":"Applying the M2 Statistic to Evaluate the Fit of Diagnostic Classification Models in the Presence of Attribute Hierarchies","year":2018,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Type I and type II errors; Statistic; Statistics; Computer science; Statistical power; Statistical model; Artificial intelligence; Econometrics; Data mining; Psychology; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08667518,0.001815142,0.001821957,0.004105347,0.001552331,0.002911344,0.00277483,0.003277173,0.004357297],"category_scores_gemma":[0.4719764,0.0008455503,0.002925655,0.003105794,0.002537443,0.004754207,0.003468004,0.004235407,0.001050207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001308926,"about_ca_system_score_gemma":0.003099529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00396613,"about_ca_topic_score_gemma":0.003815945,"domain_scores_codex":[0.9304779,0.05247582,0.003424369,0.007209672,0.005633631,0.0007786367],"domain_scores_gemma":[0.5025154,0.4571083,0.008018486,0.02244443,0.008041861,0.001871466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01230812,0.002423971,0.4061585,0.002320025,0.01508443,0.001327446,0.006976892,0.1551722,0.005344461,0.03527119,0.02761897,0.3299937],"study_design_scores_gemma":[0.0008720862,0.003864277,0.06468675,0.0004048685,0.001228856,0.0009311584,0.002516114,0.8303158,0.003965328,0.08562162,0.005298045,0.0002951667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.546183,0.00127417,0.4419665,0.001196189,0.0004675055,0.0007092322,0.001454454,0.001798715,0.004950134],"genre_scores_gemma":[0.9095851,0.0001176599,0.08744787,0.0001732157,0.00005256949,0.0005299274,0.001397718,0.0002866431,0.0004093273],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.08667518,"threshold_uncertainty_score":0.4583877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2311074073126998,"score_gpt":0.479832569862756,"score_spread":0.2487251625500562,"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."}}