{"id":"W3176262247","doi":"10.21031/epod.800697","title":"PISA 2015 Reading Test Item Parameters Across Language Groups: A measurement Invariance Study with Binary Variables","year":2021,"lang":"en","type":"article","venue":"Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi","topic":"Reading and Literacy Development","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Comparability; Measurement invariance; Equivalence (formal languages); Test (biology); Psychology; Reading (process); Mathematics education; First language; Scale (ratio); Linguistics; Confirmatory factor analysis; Mathematics; Statistics; Structural equation modeling; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002487548,0.000967122,0.001119001,0.0003826783,0.0006060149,0.0005211221,0.0007928567,0.0003298784,0.001054642],"category_scores_gemma":[0.001136489,0.0008844323,0.0002307846,0.001556886,0.0002264526,0.0005235662,0.0003369458,0.0008865497,0.001229827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006635075,"about_ca_system_score_gemma":0.0004031028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007262273,"about_ca_topic_score_gemma":0.0004061312,"domain_scores_codex":[0.9923853,0.0009613817,0.001275175,0.002084044,0.001425678,0.001868431],"domain_scores_gemma":[0.9949072,0.001482806,0.0005637034,0.001891402,0.0006333677,0.0005215182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002469193,0.01510752,0.4971047,0.0005095369,0.006670868,0.04679638,0.3021314,0.0009129112,0.02561127,0.001851515,0.08260097,0.01823372],"study_design_scores_gemma":[0.02403181,0.008025064,0.56129,0.00347136,0.001403706,0.005552863,0.2968434,0.0008283061,0.01608465,0.0006934465,0.07403534,0.007740121],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9831401,0.002654346,0.001700867,0.0007407218,0.001666337,0.001278708,0.0002079842,0.0004334194,0.008177592],"genre_scores_gemma":[0.9823576,0.00005176476,0.008834627,0.0009398881,0.0002806388,0.0006754243,0.0002042542,0.0002049475,0.006450891],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06418525,"threshold_uncertainty_score":0.9998586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03003032682645331,"score_gpt":0.3147869939598679,"score_spread":0.2847566671334146,"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."}}