{"id":"W1981221874","doi":"10.1177/0013164403261051","title":"A Note on How to Quantify and Report Whether Irt Parameter Invariance Holds: When Pearson Correlations are Not Enough","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Item response theory; Measurement invariance; Pearson product-moment correlation coefficient; Mathematics; Econometrics; Statistics; Scale (ratio); Measure (data warehouse); Correlation; Psychology; Psychometrics; Confirmatory factor analysis; Computer science; Structural equation modeling; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005228688,0.0001955677,0.0002957988,0.0002365564,0.000276062,0.0002883537,0.0002997609,0.0001248259,0.0002089257],"category_scores_gemma":[0.06219046,0.0001287343,0.00006779595,0.0006376781,0.0001126881,0.0001269226,0.00006224519,0.0002604339,0.0000945006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007410339,"about_ca_system_score_gemma":0.00005632257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002900305,"about_ca_topic_score_gemma":0.00001274242,"domain_scores_codex":[0.99652,0.0003189657,0.0004921851,0.0009272744,0.001465384,0.0002762033],"domain_scores_gemma":[0.9934185,0.005073769,0.0003184405,0.0005053644,0.0004233784,0.0002605563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001060827,0.005557962,0.4999641,0.00004088665,0.0001702833,0.000121387,0.007542775,0.0009446129,0.005681368,0.06386925,0.1283634,0.2866831],"study_design_scores_gemma":[0.0003620776,0.0003259489,0.8711762,0.00006578492,0.00000814466,0.00009021415,0.0002225405,0.00001019364,0.00003351469,0.1050626,0.02245886,0.0001839153],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7591046,0.0004419774,0.03144462,0.201983,0.001913612,0.000511174,0.00001601098,0.00004126283,0.004543674],"genre_scores_gemma":[0.9336081,0.0000206525,0.0611322,0.00398329,0.0002699507,0.00007005443,0.000002542926,0.000007836528,0.0009053679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3712122,"threshold_uncertainty_score":0.9457091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7338274295775041,"score_gpt":0.4936132193884701,"score_spread":0.240214210189034,"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."}}