{"id":"W2555293682","doi":"10.5539/hes.v6n4p181","title":"Students’ and Teacher’s Experiences of the Validity and Reliability of Assessment in a Bioscience Course","year":2016,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Reliability (semiconductor); Recall; Validity; Perception; Mathematics education; Alternative assessment; Quality (philosophy); Medical education; Test validity; Psychometrics; Developmental psychology; Medicine; Cognitive psychology","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":[0.04037908,0.00040405,0.0008457216,0.001531885,0.003217272,0.005633726,0.001060337,0.001597234,0.001197512],"category_scores_gemma":[0.1295651,0.0006071621,0.0006853049,0.0007880012,0.00413738,0.001963553,0.00427377,0.003448928,0.0003329777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002877141,"about_ca_system_score_gemma":0.002157925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002945065,"about_ca_topic_score_gemma":0.003320586,"domain_scores_codex":[0.9317889,0.05074941,0.003379085,0.002080236,0.008891364,0.003111024],"domain_scores_gemma":[0.8382107,0.117083,0.01357208,0.004616175,0.01957695,0.006941201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003014356,0.0004684317,0.07718848,0.0002190914,0.00005307684,0.001420109,0.8708826,0.0004266954,0.004482153,0.0006724073,0.000840084,0.04304557],"study_design_scores_gemma":[0.00006426488,0.002345061,0.1273392,0.0004712956,0.0001072031,0.003156754,0.8326645,0.002565286,0.009676304,0.001033181,0.02025026,0.000326641],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951833,0.0001522883,0.001111324,0.0006590703,0.00002686642,0.00002280504,0.000006050161,0.00001551289,0.002822782],"genre_scores_gemma":[0.9988556,0.00006547181,0.0003761277,0.00005849175,0.00000881694,0.00001539066,0.000006002175,0.000007262286,0.0006068663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04037908,"threshold_uncertainty_score":0.2135475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09076394953386803,"score_gpt":0.4697572589009536,"score_spread":0.3789933093670856,"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."}}