{"id":"W4380684403","doi":"10.5430/wjel.v13n6p402","title":"Rasch Calibration and Differential Item Functioning (DIF) Analysis of the Indonesian National Assessment Program-Language (INAP-L)","year":2023,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rasch model; Differential item functioning; Item response theory; Psychometrics; Polytomous Rasch model; Psychology; Calibration; Internal consistency; Item bank; Statistics; Clinical psychology; Developmental psychology; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02844521,0.0008454513,0.001113175,0.003599382,0.0008881992,0.001749225,0.0007040309,0.0004168694,0.001967866],"category_scores_gemma":[0.07148623,0.0004442037,0.002326492,0.003321202,0.0008136139,0.001392822,0.00167653,0.001236147,0.0005603114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005007,"about_ca_system_score_gemma":0.001993127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003055358,"about_ca_topic_score_gemma":0.004812225,"domain_scores_codex":[0.9783272,0.01279137,0.001855292,0.001505471,0.004976846,0.0005437442],"domain_scores_gemma":[0.9593939,0.02381452,0.003700837,0.004455727,0.008287996,0.0003470327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002831025,0.0002751192,0.799489,0.0003717871,0.0007721915,0.0001425017,0.003073453,0.004935912,0.001038428,0.002652047,0.002046843,0.1849197],"study_design_scores_gemma":[0.00004759278,0.0007818267,0.9539108,0.0003226496,0.0002940006,0.0003383662,0.002823203,0.03068704,0.001839313,0.003879915,0.004965459,0.0001097838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9122573,0.0005635418,0.07178055,0.0003639561,0.0001736545,0.001039846,0.001349791,0.0004314199,0.01203985],"genre_scores_gemma":[0.9632072,0.0001986332,0.03362017,0.000055737,0.00002047737,0.00102381,0.0009808766,0.00005442825,0.000838686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02844521,"threshold_uncertainty_score":0.1504345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01789979185604344,"score_gpt":0.3233153505967412,"score_spread":0.3054155587406978,"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."}}