{"id":"W4200186911","doi":"10.21083/ajote.v10i2.6762","title":"Analysis of Item Writing Flaws in a Communications Skills Test in a Ghanaian University","year":2021,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Multiple choice; Multitude; Quality (philosophy); First language; Mathematics education; Descriptive statistics; Item analysis; Social psychology; Statistics; Linguistics; Psychometrics; 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":[0.006162721,0.0004377913,0.0006264001,0.003716722,0.0005408721,0.0009000371,0.0005380038,0.0005256282,0.0009343931],"category_scores_gemma":[0.04313047,0.0003042479,0.0005375102,0.003986399,0.0009836541,0.0008891831,0.0008159007,0.000774116,0.0001954977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260281,"about_ca_system_score_gemma":0.001060688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002739356,"about_ca_topic_score_gemma":0.00370455,"domain_scores_codex":[0.9957249,0.001312837,0.0009234307,0.0002639026,0.001498245,0.0002766607],"domain_scores_gemma":[0.9515698,0.02172602,0.0171091,0.001624305,0.006857286,0.001113513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001262222,0.0001160202,0.9724486,0.00007335156,0.00002430126,0.0005319879,0.005285782,0.0001995822,0.00148323,0.00008161976,0.0001399226,0.01948933],"study_design_scores_gemma":[0.000007038959,0.0003431864,0.9923614,0.00003957853,0.00001736042,0.0009304563,0.003920967,0.0007370444,0.001178802,0.00008491532,0.0003676606,0.00001150281],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9992148,0.00005469743,0.0003748491,0.00003655336,0.000003423568,0.00003474894,0.00004649155,0.000005624504,0.000228875],"genre_scores_gemma":[0.9985988,0.00004934265,0.001075789,0.00001414211,0.00000239362,0.00002929889,0.00009253353,0.0000029225,0.0001348354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006162721,"threshold_uncertainty_score":0.03259194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02527638234198573,"score_gpt":0.3559029099377932,"score_spread":0.3306265275958075,"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."}}