{"id":"W2142200036","doi":"10.1002/sim.3110","title":"Reliability analysis for continuous measurements: Equivalence test for agreement","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Western Hospital; University Health Network; Memorial University of Newfoundland; Canadian Blood Services; University of Toronto","funders":"","keywords":"Repeatability; Equivalence (formal languages); Reliability (semiconductor); Inter-rater reliability; Computer science; Reliability engineering; Intra-rater reliability; Statistics; Test (biology); Consistency (knowledge bases); Mathematics; Rating scale; 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0517654,0.0002748126,0.0009244097,0.0006316443,0.0002033475,0.00005891427,0.0008814587,0.0001004554,0.0006228099],"category_scores_gemma":[0.0931019,0.0001937647,0.0001781178,0.001662904,0.0004073785,0.0001125283,0.00007777477,0.0001686107,0.00002031394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003507449,"about_ca_system_score_gemma":0.00008869886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001318625,"about_ca_topic_score_gemma":0.001169081,"domain_scores_codex":[0.9924874,0.0001699303,0.002365468,0.0009747833,0.003288802,0.0007135741],"domain_scores_gemma":[0.9791664,0.01648103,0.0005760595,0.001063798,0.00248739,0.0002253543],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001004784,0.001353057,0.7889188,0.0002876765,0.0004053562,0.00001283408,0.001673238,0.003345499,0.004115014,0.01113095,0.08845501,0.09929781],"study_design_scores_gemma":[0.007352343,0.003992951,0.5142854,0.0002342823,0.001170199,0.000001222085,0.00407656,0.01746142,0.001220347,0.3865453,0.06289697,0.0007629939],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01004945,0.0001833444,0.9830931,0.001515992,0.0008430755,0.002070747,0.0004803728,0.00002082432,0.001743106],"genre_scores_gemma":[0.8380165,0.00003212174,0.1591485,0.0007489221,0.0003067246,0.000198937,0.00009821016,0.00001535023,0.001434737],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.827967,"threshold_uncertainty_score":0.9764071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2076967185162903,"score_gpt":0.4449493606354994,"score_spread":0.237252642119209,"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."}}