{"id":"W6962179240","doi":"10.15456/jae.2023100.1646086306","title":"Multiple testing with covariate adjustment in experimental economics (replication data)","year":2023,"lang":"en","type":"other","venue":"ZBW Journal Data Archive","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Covariate; Replication (statistics); Experimental data; Statistical hypothesis testing; Multiple comparisons problem; Design of experiments","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001081135,0.000499876,0.0005490457,0.0007845598,0.0001315437,0.0001819591,0.003545376,0.0001096229,0.0002636326],"category_scores_gemma":[0.0006971476,0.0004546506,0.0000325825,0.0002911326,0.0001359629,0.0007539216,0.00274203,0.0009171041,0.00209614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004031045,"about_ca_system_score_gemma":0.0004951094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002667879,"about_ca_topic_score_gemma":0.01581324,"domain_scores_codex":[0.9967132,0.0002400894,0.0006693964,0.001459234,0.0003374375,0.0005806691],"domain_scores_gemma":[0.9926693,0.0004723901,0.001273957,0.005305495,0.00002470268,0.0002541108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003387238,0.0004527998,0.003335415,0.00004284422,0.0006039352,0.000356755,0.0004024902,0.0007799693,0.001347447,0.0001221133,0.9793323,0.01288519],"study_design_scores_gemma":[0.005409149,0.0002645759,0.009167723,0.002360481,0.0002446747,0.001446523,0.0007925668,0.07590039,0.0001161935,0.0002316024,0.9026926,0.00137359],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.003657257,0.00600617,0.009237862,0.0003902286,0.00356462,0.007274971,0.7233893,0.003179063,0.2433005],"genre_scores_gemma":[0.00467383,0.005031873,0.5184561,0.0004166023,0.009533994,0.0003402557,0.3979455,0.02135393,0.04224792],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.5092183,"threshold_uncertainty_score":0.9997905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1702734605285816,"score_gpt":0.339157570831038,"score_spread":0.1688841103024565,"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."}}