{"id":"W2329561122","doi":"10.4995/head15.2015.364","title":"Mixed-format exams in higher education: Assessment of internal consistency reliability","year":2015,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Reliability (semiconductor); Internal consistency; Measure (data warehouse); Consistency (knowledge bases); Computer science; Multiple choice; Reproducibility; Mathematics education; Test (biology); Psychology; Statistics; Mathematics; Significant difference; Psychometrics; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06445231,0.000995514,0.001325053,0.004484947,0.0008501837,0.00166718,0.001120882,0.0009095832,0.001171481],"category_scores_gemma":[0.1077917,0.0006248296,0.002498301,0.003937576,0.001369925,0.001352511,0.002350926,0.001179511,0.0006609021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006804227,"about_ca_system_score_gemma":0.0009328901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00079578,"about_ca_topic_score_gemma":0.001298573,"domain_scores_codex":[0.9597335,0.01984093,0.006086797,0.002942203,0.01066637,0.0007302784],"domain_scores_gemma":[0.8659602,0.07338359,0.01520989,0.01213691,0.03207065,0.001238839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001349662,0.0008032589,0.7720533,0.001206799,0.003384794,0.0001865948,0.007179214,0.003731483,0.005807169,0.003522683,0.004985473,0.1957896],"study_design_scores_gemma":[0.0001953638,0.002320727,0.9555492,0.0004507485,0.0007980269,0.0006654595,0.001875293,0.0138803,0.008562534,0.005735914,0.009773718,0.0001926283],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8818587,0.002725344,0.09392709,0.000337878,0.000458627,0.002621633,0.001005307,0.0004721565,0.01659315],"genre_scores_gemma":[0.9492041,0.0004331089,0.04642016,0.00009901988,0.0001084039,0.001803259,0.0007281899,0.0001141557,0.001089605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06445231,"threshold_uncertainty_score":0.3408604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7094676573679086,"score_gpt":0.5307209581113188,"score_spread":0.1787466992565898,"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."}}