{"id":"W3045826065","doi":"10.1007/s40614-020-00263-x","title":"How Many Tiers Do We Need? Type I Errors and Power in Multiple Baseline Designs","year":2020,"lang":"en","type":"article","venue":"Perspectives on Behavior Science","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institut universitaire en santé mentale de Montréal; Institut Universitaire en Santé Mentale de Québec; Université du Québec à Montréal","funders":"","keywords":"Baseline (sea); Type I and type II errors; Multiple baseline design; Computer science; Power (physics); Statistical power; Replicate; Word error rate; Reliability engineering; Statistics; Empirical research; Mathematics; Psychology; Artificial intelligence; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003412364,0.0002217231,0.0002396798,0.0001565219,0.0002337882,0.0001043122,0.000381222,0.00009082878,0.0004651679],"category_scores_gemma":[0.0002052365,0.000171941,0.00005010196,0.001177145,0.001125918,0.0001896677,0.0001062478,0.0003462168,0.00009442393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007784266,"about_ca_system_score_gemma":0.00002010958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006952882,"about_ca_topic_score_gemma":0.0000113617,"domain_scores_codex":[0.9980036,0.00009547939,0.0001608324,0.0009451621,0.0003166312,0.0004782691],"domain_scores_gemma":[0.999247,0.00008063484,0.00006236728,0.0002489394,0.0001009445,0.0002600897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008246354,0.00209922,0.7915878,0.000006874072,0.00001643209,0.0003635254,0.1016324,0.000005048987,0.04368031,0.009921885,0.001983815,0.04787806],"study_design_scores_gemma":[0.0008762459,0.001311342,0.9038948,0.00001702159,0.00002355777,0.00001163727,0.09103556,0.00002608401,0.0002430889,0.00007906132,0.002103892,0.0003776926],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856655,0.001801442,0.0001023302,0.00992595,0.0004084325,0.0003729075,0.00001653392,0.0000800158,0.001626872],"genre_scores_gemma":[0.9983929,0.0001461318,0.0005537245,0.0003933823,0.00004179549,0.00005457587,5.34046e-7,0.0000131487,0.0004037915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1123071,"threshold_uncertainty_score":0.7011549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.223927285176199,"score_gpt":0.3654105172447536,"score_spread":0.1414832320685546,"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."}}