{"id":"W4415917134","doi":"10.1002/asmb.70052","title":"A Comprehensive Framework for Statistical Inference in Measurement System Assessment Studies","year":2025,"lang":"en","type":"article","venue":"Applied Stochastic Models in Business and Industry","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistical inference; Estimator; Variance (accounting); Key (lock); Inference; Statistical model; System of measurement; Variance components","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":[],"consensus_categories":[],"category_scores_codex":[0.004818876,0.0002156496,0.0005563632,0.0005120491,0.0001714465,0.0002030089,0.0003172703,0.000274493,0.0000144814],"category_scores_gemma":[0.003373199,0.0001695849,0.00002406539,0.001351915,0.0001728322,0.0001488968,0.0001518948,0.0003992048,0.000002239653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003890483,"about_ca_system_score_gemma":0.0004520202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004839514,"about_ca_topic_score_gemma":0.00008598512,"domain_scores_codex":[0.996298,0.000116423,0.0009239856,0.0007289367,0.001596548,0.0003360951],"domain_scores_gemma":[0.9948409,0.003071358,0.0001903033,0.0003735777,0.001461075,0.00006284165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001082286,0.00007810787,0.0005078506,0.0001258132,0.00002424841,0.000001153468,0.0003741865,0.2314323,0.00008305837,0.7506728,0.0003389416,0.01625336],"study_design_scores_gemma":[0.001380228,0.00001782839,0.01468917,0.0007501162,0.00002712381,3.379873e-7,0.008348163,0.4397942,0.000008410559,0.5347514,0.00004874032,0.0001843885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03972637,0.000296218,0.9567053,0.0005683699,0.0006578616,0.001098509,0.00001581135,0.00001847884,0.0009131262],"genre_scores_gemma":[0.990024,0.000005690044,0.00918239,0.0001223926,0.00003654698,0.0005836657,0.000005457891,0.000006631407,0.0000332275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9502977,"threshold_uncertainty_score":0.6915473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4347812240265034,"score_gpt":0.4788136776576259,"score_spread":0.04403245363112251,"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."}}