{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002257226,0.0001235244,0.0003034937,0.0001043163,0.00007718997,0.000007941431,0.000652544,0.00006437004,0.00001121035],"category_scores_gemma":[0.006116294,0.00006505963,0.00003490462,0.0004148709,0.0006654072,0.00005378107,0.00006355402,0.0002463032,0.000001902044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001836607,"about_ca_system_score_gemma":0.00002529408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002131411,"about_ca_topic_score_gemma":0.000041002,"domain_scores_codex":[0.9976423,0.001023733,0.0005371868,0.0002629124,0.0002615592,0.0002722981],"domain_scores_gemma":[0.9907018,0.008312919,0.0001615607,0.0006891122,0.0001081733,0.00002643569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003883695,0.0003638331,0.002330519,0.0001337359,0.00006348677,0.000006194581,0.01678469,0.001823259,0.0005789599,0.6162732,0.03704394,0.3242098],"study_design_scores_gemma":[0.0003186283,0.0001526973,0.003984651,0.00005832686,0.0000279717,0.000002746005,0.001427788,0.0358876,0.00004482021,0.9574507,0.0005716279,0.00007248094],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01056116,0.0002272139,0.984968,0.001524654,0.000399703,0.001475452,0.00006511934,0.000006464463,0.0007722336],"genre_scores_gemma":[0.5806441,0.0001300338,0.4178861,0.0003894178,0.00003787563,0.0008748778,0.000002211936,0.00001299874,0.00002241596],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5700829,"threshold_uncertainty_score":0.7322217,"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."}}