{"id":"W2340568370","doi":"10.1187/cbe.15-06-0131","title":"Development of the Statistical Reasoning in Biology Concept Inventory (SRBCI)","year":2016,"lang":"en","type":"article","venue":"CBE—Life Sciences Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Rasch model; Statistical thinking; Concept inventory; Construct (python library); Mathematics education; Item response theory; Test (biology); Scientific reasoning; Critical thinking; Psychology; Computer science; Psychometrics; Biology; Developmental psychology; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01372841,0.0007181115,0.0009612993,0.003938251,0.000975172,0.001767686,0.001907151,0.0005530471,0.005415446],"category_scores_gemma":[0.03166319,0.0007088366,0.001393744,0.002684319,0.001157508,0.00136254,0.002042038,0.003130784,0.002306338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00359625,"about_ca_system_score_gemma":0.0143101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0231334,"about_ca_topic_score_gemma":0.04626308,"domain_scores_codex":[0.9943076,0.001046686,0.000799885,0.0003499839,0.003153177,0.0003427255],"domain_scores_gemma":[0.9706788,0.008400275,0.002751139,0.001767855,0.01461427,0.001787686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004074137,0.003587265,0.2667879,0.001158885,0.0002073208,0.000396501,0.01035176,0.004809506,0.008322247,0.01031068,0.03248514,0.6611754],"study_design_scores_gemma":[0.0002956798,0.002118564,0.7957884,0.0007410113,0.0002045513,0.000557823,0.004768261,0.0172694,0.01307443,0.01146229,0.1533264,0.0003932639],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6426683,0.001141924,0.2200761,0.002204775,0.0005698921,0.06024489,0.01894684,0.002446513,0.05170069],"genre_scores_gemma":[0.2826616,0.00127387,0.6219424,0.0007385504,0.0001145178,0.06608667,0.0142429,0.0004180968,0.01252135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0231334,"threshold_uncertainty_score":0.07260364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2316813360292487,"score_gpt":0.4847709360024541,"score_spread":0.2530895999732055,"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."}}