{"id":"W2036060563","doi":"10.1186/1471-2288-10-82","title":"Inter-rater agreement and reliability of the COSMIN (COnsensus-based Standards for the selection of health status Measurement Instruments) Checklist","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":289,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Vrije Universiteit Amsterdam; University of Oxford; McMaster University; Goddard Space Flight Center; University of Washington","keywords":"Checklist; Kappa; Inter-rater reliability; Intraclass correlation; Cohen's kappa; Reliability (semiconductor); Medicine; Quality (philosophy); Agreement; Terminology; Psychology; Applied psychology; Physical therapy; Medical physics; Clinical psychology; Statistics; Psychometrics; Rating scale; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"category_scores_codex":[0.4358364,0.001445731,0.004907385,0.01960988,0.00250904,0.003799732,0.002722132,0.001870401,0.002273305],"category_scores_gemma":[0.5637624,0.001302706,0.006765738,0.01049603,0.002957994,0.003346483,0.006372036,0.001666486,0.0006816107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003326969,"about_ca_system_score_gemma":0.007912249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001977661,"about_ca_topic_score_gemma":0.003499456,"domain_scores_codex":[0.4615676,0.3050374,0.1589624,0.01472402,0.05723077,0.002477792],"domain_scores_gemma":[0.2919052,0.3872869,0.0759158,0.03428093,0.2079939,0.002617242],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00883135,0.0007415926,0.4160748,0.08138403,0.01958575,0.0009746623,0.07698122,0.004196166,0.01436923,0.00642896,0.02400911,0.3464232],"study_design_scores_gemma":[0.005621792,0.005573693,0.730319,0.06042423,0.02111987,0.002687831,0.0294494,0.02886988,0.02352265,0.01435929,0.07632324,0.00172913],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.593768,0.04515981,0.2468248,0.003392881,0.003150086,0.07143614,0.01232044,0.001221075,0.02272671],"genre_scores_gemma":[0.6843109,0.005268272,0.2060467,0.0005434036,0.0004476904,0.09748134,0.004410341,0.0004011316,0.00109023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5641636,"threshold_uncertainty_score":0.6957142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5948043968788056,"score_gpt":0.5666070490965269,"score_spread":0.02819734778227867,"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."}}