{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.394015,0.0001699311,0.0006664849,0.0002072472,0.0004807004,0.000051671,0.001216097,0.0002002344,0.001058631],"category_scores_gemma":[0.3844943,0.00007941615,0.0002122274,0.0007389415,0.002842776,0.00004208873,0.0004454363,0.00094143,0.000002441472],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003325753,"about_ca_system_score_gemma":0.00629961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001463431,"about_ca_topic_score_gemma":0.009785491,"domain_scores_codex":[0.9401533,0.03720393,0.003069788,0.001145841,0.01720643,0.001220689],"domain_scores_gemma":[0.9302254,0.06034505,0.0008108895,0.001648001,0.006530828,0.000439812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002453449,0.0008920706,0.3676997,0.0008563165,0.00009789977,3.107363e-7,0.001033717,0.0001358515,0.01665502,0.002569515,0.01801015,0.589596],"study_design_scores_gemma":[0.007085396,0.004468236,0.5668253,0.0006157815,0.0000784599,0.000008793487,0.005424237,0.02663061,0.07637274,0.07185221,0.2402325,0.0004056925],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7360402,0.0002679026,0.2360404,0.02366712,0.001168196,0.00253549,0.00008794098,0.000008788287,0.0001840239],"genre_scores_gemma":[0.9704114,0.00007649354,0.02881524,0.0003273527,0.00007062288,0.0001740064,0.000001368642,0.000008853127,0.000114639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5891903,"threshold_uncertainty_score":0.9998709,"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."}}