{"id":"W3112901974","doi":"10.1002/sim.8848","title":"Mean comparisons and power calculations to ensure reproducibility in preclinical drug discovery","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Animal testing and alternatives","field":"Veterinary","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Reproducibility; Sample size determination; Statistical power; Statistics; Computer science; Power analysis; Statistical hypothesis testing; Power (physics); Sample (material); Multiple comparisons problem; Data mining; False discovery rate; Reliability engineering; Mathematics; Algorithm; Chemistry","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001019409,0.0001104816,0.0003133833,0.00005142399,0.00003439269,0.00001071599,0.00009848484,0.00002650025,0.00005978229],"category_scores_gemma":[0.01300297,0.00009286829,0.00001054559,0.0002036891,0.0001773882,0.00004777158,0.0001060548,0.0003104786,0.000009086447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002660559,"about_ca_system_score_gemma":0.00002437661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000431118,"about_ca_topic_score_gemma":0.0004091747,"domain_scores_codex":[0.9983538,0.0001755524,0.0004548524,0.0006765365,0.000180791,0.0001584052],"domain_scores_gemma":[0.9980942,0.001340052,0.00006389179,0.000332885,0.00004047711,0.0001285183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007108901,0.0002235606,0.9227334,0.0001232533,0.00002402355,0.0004028108,0.02568142,0.0001331474,0.0008747748,0.02177913,0.02531962,0.001994005],"study_design_scores_gemma":[0.0007572565,0.0009893201,0.9858893,0.0001969708,0.00001409823,0.000007365448,0.001681196,0.005168814,0.000008033847,0.003879297,0.001263167,0.0001452341],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9681965,0.0001865646,0.02062386,0.008330415,0.0001356889,0.0002801027,0.000206777,0.000038642,0.002001514],"genre_scores_gemma":[0.9804237,0.000007882827,0.01860543,0.0006978888,0.0001299984,0.000007059466,0.00002487302,0.00001143814,0.00009170971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06315588,"threshold_uncertainty_score":0.9953109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2575619557973964,"score_gpt":0.4845432090676691,"score_spread":0.2269812532702726,"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."}}