{"id":"W2054195447","doi":"10.2466/pr0.103.2.545-565","title":"On the Integrity of Reliability Estimation in Classical Test Theory: The Case for an Additive Coefficient of Stability","year":2008,"lang":"en","type":"article","venue":"Psychological Reports","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Generalizability theory; Estimator; Reliability (semiconductor); Classical test theory; Econometrics; Estimation; Stability (learning theory); Reliability engineering; Computer science; Scale (ratio); Statistics; Test (biology); Mathematics; Item response theory; Psychometrics; Machine learning; 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":[],"category_scores_codex":[0.004945474,0.0001257602,0.000335561,0.00001838964,0.00009953097,0.000003517624,0.0001114062,0.00011871,0.00006611757],"category_scores_gemma":[0.08151191,0.00005696818,0.00009956678,0.0001474637,0.0008182352,0.00003501928,0.00003306544,0.0003758724,2.391749e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004098195,"about_ca_system_score_gemma":0.00002550469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000115561,"about_ca_topic_score_gemma":0.00001363934,"domain_scores_codex":[0.9977753,0.0006923831,0.0007518554,0.0003798741,0.000229021,0.0001715403],"domain_scores_gemma":[0.971767,0.02683951,0.0003821334,0.0007154821,0.0002390848,0.00005675225],"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":[0.0006325747,0.006047778,0.0005924348,0.00005182546,0.00001045759,0.0003470125,0.001394912,0.0003374011,0.0002931043,0.9711432,0.0004388856,0.01871035],"study_design_scores_gemma":[0.0001564478,0.0008955906,0.004257988,0.00002209204,0.0000140748,0.0002940778,0.0002726478,0.009523269,0.0007602074,0.9837164,0.00001743377,0.00006978723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5586385,0.000002521736,0.4397511,0.0001753667,0.00004071434,0.0006298896,0.00007126095,0.00001141254,0.0006792024],"genre_scores_gemma":[0.9018758,0.000001938168,0.09790928,0.00006180867,0.000008429134,0.000124155,0.000003864236,0.000006555235,0.000008184489],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3432373,"threshold_uncertainty_score":0.9262249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2583452377276964,"score_gpt":0.4824129585210412,"score_spread":0.2240677207933448,"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."}}