{"id":"W4383815387","doi":"10.56230/osotl.16","title":"Does it matter when it happens? Assessing whether formative quizzes at different timepoints in a course are predictive of final exam grades","year":2023,"lang":"en","type":"article","venue":"Open Scholarship of Teaching and Learning","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Summative assessment; Formative assessment; Academic achievement; Psychology; Medical education; Predictive value; Mathematics education; Medicine; Internal medicine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007298043,0.0002869963,0.0005823305,0.001142513,0.0005427907,0.002966963,0.00053643,0.0009315587,0.001749489],"category_scores_gemma":[0.05390718,0.0001914379,0.0005386377,0.001209662,0.0009525543,0.001244597,0.000682905,0.001077301,0.00060143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006362549,"about_ca_system_score_gemma":0.001010258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003764074,"about_ca_topic_score_gemma":0.006413273,"domain_scores_codex":[0.9964423,0.001422526,0.0003331355,0.000578589,0.0008464896,0.0003769082],"domain_scores_gemma":[0.947861,0.02376343,0.01742508,0.001821954,0.004104196,0.005024267],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002027716,0.0002539165,0.9857679,0.00002576536,0.0001085164,0.00002662099,0.0008684772,0.0001143814,0.0003897287,0.0001036696,0.0002147236,0.01192368],"study_design_scores_gemma":[0.000004702184,0.0002963724,0.9977968,0.00001808475,0.00003775488,0.00002128502,0.0008438949,0.0003365825,0.0002371737,0.0001929999,0.0002044663,0.000009891949],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975241,0.0001994347,0.0004289724,0.0003524765,0.00003041759,0.00001993682,0.00007205852,0.00001353046,0.001359018],"genre_scores_gemma":[0.9991836,0.0001011139,0.0002151695,0.00005780117,0.00001606373,0.00001236568,0.00006182188,0.000004591319,0.0003474446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9927019,"threshold_uncertainty_score":0.03859615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1625747681532041,"score_gpt":0.4553232299467115,"score_spread":0.2927484617935074,"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."}}