{"id":"W4242378879","doi":"10.31234/osf.io/rd5sc","title":"Evaluating Equivalence Testing Methods for Measurement Invariance","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; York University","funders":"","keywords":"Equivalence (formal languages); Goodness of fit; Mathematics; Statistics; Type I and type II errors; Sample size determination; Chi-square test; Significant difference; Test (biology); Applied mathematics; Econometrics; Discrete 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2262184,0.00325367,0.003737752,0.007306488,0.002763498,0.005694721,0.004969638,0.003075634,0.01573003],"category_scores_gemma":[0.6876379,0.001161784,0.006613434,0.008885492,0.009198864,0.01006748,0.007603314,0.008214159,0.001934768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003576314,"about_ca_system_score_gemma":0.00514896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002452198,"about_ca_topic_score_gemma":0.001641792,"domain_scores_codex":[0.6771104,0.2470133,0.01502163,0.02329285,0.03580905,0.001752839],"domain_scores_gemma":[0.2881714,0.6201371,0.01991034,0.04472448,0.02553811,0.001518561],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001318368,0.0007583341,0.05058426,0.003010134,0.006371132,0.0003632445,0.004280371,0.01885785,0.001807477,0.3555455,0.0123058,0.5447975],"study_design_scores_gemma":[0.001128203,0.004173959,0.04419483,0.002622532,0.001893481,0.0006546827,0.002711449,0.1810908,0.005060514,0.7235909,0.03237967,0.0004990367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02004322,0.001077511,0.9641222,0.001106651,0.0006988015,0.002365423,0.0005768951,0.0005910916,0.009418148],"genre_scores_gemma":[0.341038,0.0007652279,0.6417912,0.000999803,0.0005286497,0.01219464,0.001002719,0.000593496,0.001086322],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7737816,"threshold_uncertainty_score":0.9542105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6838608469192291,"score_gpt":0.5568467355373146,"score_spread":0.1270141113819145,"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."}}