{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05747062,0.001159416,0.001246415,0.002166844,0.00107156,0.002559958,0.0025529,0.002342937,0.006288734],"category_scores_gemma":[0.3325682,0.0004822288,0.002372015,0.001721076,0.002017325,0.004075697,0.001639889,0.003163166,0.0009834325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009234472,"about_ca_system_score_gemma":0.002424742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004346375,"about_ca_topic_score_gemma":0.003053395,"domain_scores_codex":[0.9491159,0.03204124,0.0036333,0.007717993,0.005804213,0.001687353],"domain_scores_gemma":[0.487472,0.4801352,0.006076159,0.0189704,0.005760252,0.001586044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005671027,0.00168954,0.655396,0.0008475376,0.004614229,0.002152646,0.003706113,0.02386867,0.01169411,0.01393193,0.00565259,0.2707756],"study_design_scores_gemma":[0.0004970945,0.006716269,0.4833003,0.0004341749,0.002417383,0.003502171,0.007657662,0.43782,0.02481551,0.02482653,0.007696903,0.0003159691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7914643,0.000431704,0.1987281,0.0009069012,0.0004010672,0.0002304889,0.0006187042,0.001086413,0.006132245],"genre_scores_gemma":[0.9694424,0.00004760323,0.02928429,0.00008524666,0.00002834709,0.00008491351,0.000388327,0.0001083084,0.0005305207],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05747062,"threshold_uncertainty_score":0.3039373,"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."}}