{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0235982,0.0002141375,0.0005464755,0.001961912,0.0002993428,0.0002721148,0.0007249079,0.000253297,0.00008136074],"category_scores_gemma":[0.03867656,0.0001670701,0.00009467835,0.005060406,0.000193179,0.0007023858,0.0005598292,0.0006086265,0.00002015956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001475955,"about_ca_system_score_gemma":0.000323437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001853136,"about_ca_topic_score_gemma":0.00002571656,"domain_scores_codex":[0.9925668,0.0025109,0.0008796324,0.00089488,0.002425374,0.0007224182],"domain_scores_gemma":[0.9647508,0.03192808,0.0003321795,0.0007913844,0.001955082,0.0002425372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001200961,0.0002122694,0.3584597,0.0000130867,0.000007796878,0.00000907324,0.0008928553,0.02387206,0.5989435,0.0000737835,0.00004082408,0.01627406],"study_design_scores_gemma":[0.0006418421,0.0002579859,0.3111648,0.00004764687,0.000007608922,0.00001046859,0.0005234853,0.6826689,0.002257345,0.002279725,0.000006758155,0.0001333437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821813,0.00003897805,0.01656867,0.00005395306,0.000163667,0.0006973714,0.00001596715,0.0000445471,0.0002355505],"genre_scores_gemma":[0.9519238,0.000004855282,0.04687808,0.000006482237,0.00002292008,0.00001561472,0.00000165249,0.00002896513,0.001117616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6587969,"threshold_uncertainty_score":0.9694211,"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."}}