{"id":"W1972548285","doi":"10.1080/13803611.2013.767624","title":"Assessing statistical aspects of test fairness with structural equation modelling","year":2013,"lang":"en","type":"article","venue":"Educational Research and Evaluation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Structural equation modeling; Test (biology); Measurement invariance; Psychology; Confirmatory factor analysis; Set (abstract data type); Econometrics; Statistical hypothesis testing; Item response theory; Social psychology; Statistics; Psychometrics; Test validity; Interpretation (philosophy); Mathematics; Computer science; Developmental psychology","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01299373,0.00007252405,0.0001390823,0.0005194827,0.0002893362,0.0005325719,0.0002015101,0.00003988286,0.001965525],"category_scores_gemma":[0.1212204,0.00004815019,0.00001244173,0.001383647,0.0002156028,0.0008394137,0.00004754601,0.0001646507,0.00004205663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007830153,"about_ca_system_score_gemma":0.0007182315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002756359,"about_ca_topic_score_gemma":0.000008790206,"domain_scores_codex":[0.9949804,0.0007247317,0.0003956738,0.0003469921,0.00331354,0.000238651],"domain_scores_gemma":[0.9068164,0.08746363,0.0002147373,0.0002720208,0.005084917,0.0001482897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000510238,0.0002189025,0.3536878,0.00004387392,0.00002585977,3.675041e-7,0.001043514,0.02011895,0.002186822,0.1255162,0.002257361,0.4948493],"study_design_scores_gemma":[0.0001011597,0.00007618684,0.3260706,0.0000123356,0.000002194918,0.000002156089,0.0008300514,0.3031575,0.00005974195,0.3696504,0.000006346218,0.00003131996],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8903921,0.0001383288,0.1000552,0.00145083,0.0001052935,0.0003536895,0.000004016052,0.00000436946,0.007496204],"genre_scores_gemma":[0.9462619,0.00000450642,0.05339193,0.000007885283,0.0001182303,0.00005482688,0.00002487934,0.000004892989,0.0001309854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4948179,"threshold_uncertainty_score":0.9989468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8738377455316619,"score_gpt":0.6435779505699563,"score_spread":0.2302597949617057,"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."}}