{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004671255,0.0003840541,0.0005179876,0.00007033809,0.0001645795,0.0002888429,0.002603673,0.0001810442,0.000004636611],"category_scores_gemma":[0.02390352,0.0003765073,0.0001204076,0.0002788987,0.00004840184,0.0002103495,0.00420716,0.000645772,0.000005997809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002941965,"about_ca_system_score_gemma":0.0005725767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002684539,"about_ca_topic_score_gemma":0.000001215366,"domain_scores_codex":[0.9961794,0.0003602807,0.0007150327,0.001520328,0.0007405785,0.0004843906],"domain_scores_gemma":[0.9947457,0.002048407,0.0004033086,0.001253507,0.001366454,0.0001826104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006122208,0.0000203245,0.000002022816,0.0003895859,0.00002252626,0.000002096678,0.0001010901,0.008345168,0.01476444,0.2278893,0.0002180819,0.7482392],"study_design_scores_gemma":[0.00006093238,0.00009764354,0.00000433406,0.0002136348,0.00001289445,0.000001140779,0.000001046819,0.5200608,0.00447693,0.4747632,0.0000746176,0.0002327826],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000001917064,0.0002513164,0.9930653,0.001857148,0.0004523734,0.001371674,0.00001018782,0.001822144,0.00116795],"genre_scores_gemma":[0.00594242,0.000006884664,0.9922612,0.0008243023,0.0001271369,0.0007793825,0.000003319972,0.0000364205,0.00001890655],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7480065,"threshold_uncertainty_score":0.9998687,"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."}}