{"id":"W1829168467","doi":"10.1191/0962280204sm365ra","title":"Sample size requirements for the design of reliability study: review and new results","year":2004,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":468,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Intraclass correlation; Sample size determination; Reliability (semiconductor); Variance (accounting); Statistics; Sample (material); Computer science; Mathematics; Reliability engineering; Psychometrics","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":[0.1698967,0.001783208,0.01084743,0.007719052,0.0007318137,0.003003042,0.005395368,0.005002054,0.003589371],"category_scores_gemma":[0.3808528,0.001750659,0.004613635,0.005878017,0.00286646,0.005736259,0.002073616,0.003539041,0.001446041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003460517,"about_ca_system_score_gemma":0.008207438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001923023,"about_ca_topic_score_gemma":0.002516401,"domain_scores_codex":[0.8679073,0.0625247,0.03389155,0.006091706,0.02890284,0.0006819613],"domain_scores_gemma":[0.4880433,0.4582752,0.01548277,0.007107106,0.03035333,0.0007382764],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001265422,0.0001273453,0.001196677,0.1143539,0.001281539,0.0003621152,0.0003874899,0.001485826,0.00186959,0.00744992,0.01351812,0.8567021],"study_design_scores_gemma":[0.005908765,0.007839526,0.03307818,0.3216825,0.03182968,0.008435185,0.001264153,0.0101416,0.01296294,0.06792659,0.497986,0.0009449044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001690314,0.9316053,0.05510847,0.00448324,0.002466118,0.002055195,0.0004679291,0.0001460712,0.001977405],"genre_scores_gemma":[0.01985671,0.7844866,0.1728505,0.004011099,0.002862861,0.01408182,0.0009313648,0.0002076802,0.0007112714],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8301033,"threshold_uncertainty_score":0.8985104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7388653050513273,"score_gpt":0.6767105014196586,"score_spread":0.0621548036316687,"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."}}