{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3059061,0.0001586218,0.0007157914,0.0001192253,0.000234616,0.00008057058,0.001493691,0.0001173259,0.001230869],"category_scores_gemma":[0.885231,0.0000838829,0.00006633768,0.001371154,0.001272959,0.00008711299,0.0005117015,0.0007985488,0.00001097812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001576554,"about_ca_system_score_gemma":0.00102483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009682967,"about_ca_topic_score_gemma":0.00008592699,"domain_scores_codex":[0.9661128,0.0174778,0.003102248,0.001373613,0.01100778,0.0009257876],"domain_scores_gemma":[0.2118028,0.781992,0.000361751,0.002526177,0.002214304,0.001102982],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008900702,0.000996033,0.001086405,0.0003816549,0.0000367946,0.000009792651,0.0006431302,0.0001015617,0.00006885325,0.01230432,0.01676285,0.9667186],"study_design_scores_gemma":[0.002557727,0.001583491,0.01666613,0.0004758434,0.00004343197,9.721886e-7,0.000704837,0.001384857,0.00008773887,0.9667127,0.009666867,0.0001153959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002772174,0.001785707,0.9649975,0.02878453,0.0001465486,0.00372231,0.00007045415,0.000007060383,0.0002086929],"genre_scores_gemma":[0.01529603,0.002371657,0.9812514,0.000588629,0.0000658162,0.0002700231,0.000001357453,0.00001042662,0.000144685],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9666032,"threshold_uncertainty_score":0.9996821,"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."}}