{"id":"W4362671389","doi":"10.3389/feduc.2023.1154592","title":"Teachers’ test construction competencies in examination-oriented educational system: Exploring teachers’ multiple-choice test construction competence","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Competence (human resources); Multiple choice; Exploratory factor analysis; Psychology; Test (biology); Mathematics education; Item analysis; Psychometrics; Social psychology; Developmental psychology; Mathematics; Statistics; Significant difference","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001164732,0.0002140812,0.000270295,0.0009348295,0.0005306202,0.0001362138,0.0003076265,0.0001546793,0.00005131622],"category_scores_gemma":[0.00335266,0.0002622949,0.00006706442,0.002271314,0.000482067,0.001104327,0.00004392123,0.0003257371,0.00005283612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001932949,"about_ca_system_score_gemma":0.0009350554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003141576,"about_ca_topic_score_gemma":0.002297734,"domain_scores_codex":[0.9975479,0.0003369838,0.0005404153,0.0004881698,0.0006150137,0.0004714738],"domain_scores_gemma":[0.997717,0.001445595,0.0002716678,0.0002152743,0.0002311927,0.0001193331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003016314,0.0002494203,0.9323246,0.00002710868,0.0000106659,5.656038e-7,0.04724164,0.00003590119,0.0001431198,0.004116197,0.002071579,0.01377617],"study_design_scores_gemma":[0.0003897549,0.00001632488,0.6485885,0.0001594205,0.00001364604,0.000001844898,0.3460614,0.0004769867,0.00001474062,0.0002336229,0.003853803,0.0001899665],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9778076,0.0001971221,0.0004995305,0.001216026,0.01172442,0.0008224514,0.00001243046,0.0002447799,0.007475661],"genre_scores_gemma":[0.9817701,0.0002054559,0.01537078,0.00002513683,0.000748767,0.0005011811,0.0001816115,0.00002235926,0.001174598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2988198,"threshold_uncertainty_score":0.999983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03220774194013364,"score_gpt":0.3025298898814719,"score_spread":0.2703221479413383,"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."}}