{"id":"W4393408830","doi":"10.3758/s13428-024-02384-6","title":"Examining the performance of the chi-square difference test when the unrestricted model is slightly misspecified","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nested set model; Context (archaeology); Statistics; Test (biology); Econometrics; Structural equation modeling; Statistical hypothesis testing; Chi-square test; Mean squared error; Mathematics; Computer science; Data mining","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":["metaresearch"],"category_scores_codex":[0.05186366,0.0002553475,0.0004141493,0.0006240141,0.001187659,0.0008299726,0.005344063,0.0001586242,0.0003523864],"category_scores_gemma":[0.1052742,0.00009607773,0.0002340314,0.007940572,0.0009662933,0.0001932107,0.001470481,0.001723878,0.00003188386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007739539,"about_ca_system_score_gemma":0.0003793967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001140757,"about_ca_topic_score_gemma":0.000005797638,"domain_scores_codex":[0.986015,0.007462552,0.0009956815,0.0008851916,0.003838476,0.0008030768],"domain_scores_gemma":[0.8402189,0.1552855,0.0002877701,0.003067341,0.0009787536,0.0001617785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002783479,0.0001010977,0.09642911,0.00003109833,0.00002010528,0.000007722775,0.004212616,0.0001026033,0.02577219,0.0009793227,0.007926655,0.8643897],"study_design_scores_gemma":[0.0001985878,0.0002764039,0.8072801,0.0001943835,0.00004611863,0.00003064945,0.003404889,0.1521252,0.01678298,0.01066877,0.008750347,0.0002415811],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9630582,0.001934663,0.02568866,0.002875705,0.0008118467,0.0009710828,0.00004713427,0.00008408113,0.004528604],"genre_scores_gemma":[0.8990797,0.0002041897,0.08926295,0.0001013746,0.0001583731,0.0002206244,8.196057e-7,0.00003409143,0.01093785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8641481,"threshold_uncertainty_score":0.9930688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8815597692413241,"score_gpt":0.6416555860264059,"score_spread":0.2399041832149181,"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."}}