{"id":"W2965155714","doi":"10.1080/00273171.2019.1633617","title":"Evaluating Equivalence Testing Methods for Measurement Invariance","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Equivalence (formal languages); Goodness of fit; Statistics; Mathematics; Type I and type II errors; Sample size determination; Chi-square test; Measurement invariance; Test (biology); Applied mathematics; Econometrics; Structural equation modeling; Discrete mathematics; Confirmatory factor analysis","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":[0.196044,0.0002754331,0.00063048,0.001039027,0.0007040942,0.0007162992,0.002341922,0.0001924631,0.0005576227],"category_scores_gemma":[0.5836906,0.0002082998,0.0001896129,0.005450974,0.0001704592,0.0004691651,0.001008316,0.0008092496,0.0003486401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003881878,"about_ca_system_score_gemma":0.0005184841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007656551,"about_ca_topic_score_gemma":0.000007283032,"domain_scores_codex":[0.9834376,0.006480236,0.001309339,0.001615469,0.005687757,0.001469594],"domain_scores_gemma":[0.7325107,0.2497923,0.0008715855,0.002957901,0.01330522,0.00056236],"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":[0.0000952273,0.0001167047,0.03614717,0.0000185905,0.000007129498,0.000001976835,0.000228186,0.0001969899,0.270252,0.000420354,0.0001561774,0.6923595],"study_design_scores_gemma":[0.005079351,0.004527288,0.4588944,0.000535751,0.00006123393,0.00002208748,0.003145099,0.3764821,0.02412616,0.1161771,0.009664318,0.001285087],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6490481,0.0004454738,0.3404704,0.0003924939,0.001823151,0.003104405,0.00001880373,0.0001580779,0.004539017],"genre_scores_gemma":[0.4287962,0.000001820357,0.5698276,0.00002270647,0.0001039351,0.000205006,0.000001170035,0.00002662875,0.001015015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6910744,"threshold_uncertainty_score":0.849422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9836237612469282,"score_gpt":0.7740472692881768,"score_spread":0.2095764919587514,"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."}}