{"id":"W2974193444","doi":"10.1080/00273171.2019.1664280","title":"Model Selection of Nested and Non-Nested Item Response Models Using Vuong Tests","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Nested set model; Item response theory; Context (archaeology); Model selection; Selection (genetic algorithm); Statistical hypothesis testing; Set (abstract data type); Statistical model","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":[0.1016084,0.002316355,0.004544401,0.005462297,0.001795773,0.004699137,0.005078042,0.002027394,0.004834604],"category_scores_gemma":[0.3788574,0.001141872,0.00595688,0.004533008,0.003444361,0.005320325,0.005441344,0.004633323,0.0006160247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002045416,"about_ca_system_score_gemma":0.004324123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004271428,"about_ca_topic_score_gemma":0.003297622,"domain_scores_codex":[0.7972298,0.1805406,0.004965242,0.009038329,0.006364276,0.00186168],"domain_scores_gemma":[0.5898135,0.3771554,0.008602138,0.01598713,0.006896209,0.001545572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002660109,0.001194365,0.1328235,0.00167257,0.007199456,0.002209158,0.006790611,0.2279248,0.001957786,0.271247,0.005949354,0.3383713],"study_design_scores_gemma":[0.0002642233,0.001501093,0.01117806,0.0002993096,0.0004016581,0.0004292516,0.001089156,0.8215594,0.001344219,0.1590145,0.00272667,0.0001924292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08054028,0.0002460978,0.9157924,0.0002965583,0.0001252435,0.0009362123,0.000280311,0.0005688347,0.001214021],"genre_scores_gemma":[0.5291041,0.0001246285,0.4662588,0.0002288995,0.00005261091,0.002887199,0.0006812551,0.0001692158,0.0004933121],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1016084,"threshold_uncertainty_score":0.5373629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8817116620456461,"score_gpt":0.6364831850108131,"score_spread":0.245228477034833,"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."}}