{"id":"W1995404757","doi":"10.1111/j.1745-3984.2009.01067.x","title":"The Reliability of Difference Scores in Populations and Samples","year":2009,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reliability (semiconductor); Statistics; Population; Variance (accounting); Mathematics; Sample (material); Sample size determination; Standard deviation; Econometrics; Demography; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0680208,0.0004848641,0.001222443,0.003740811,0.0006008011,0.002639203,0.001553563,0.001551407,0.001080431],"category_scores_gemma":[0.4520124,0.000879377,0.0008822267,0.00214699,0.00543419,0.003381425,0.003787454,0.00187198,0.0003787413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001119111,"about_ca_system_score_gemma":0.0008857125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001755256,"about_ca_topic_score_gemma":0.0008082017,"domain_scores_codex":[0.924015,0.0484737,0.003912327,0.009264891,0.01358661,0.0007474637],"domain_scores_gemma":[0.6228648,0.3158165,0.01335595,0.03185407,0.01531482,0.0007937996],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001801536,0.0002639465,0.5846543,0.000950475,0.002116921,0.0005371086,0.01180402,0.07848589,0.006271826,0.1029192,0.001598546,0.2085962],"study_design_scores_gemma":[0.0002631333,0.001351576,0.4651974,0.0005820784,0.0007287806,0.002412417,0.003328127,0.2423487,0.01044961,0.2657985,0.00711423,0.0004254018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6710046,0.0009633605,0.3228044,0.0002749214,0.000101941,0.0002264955,0.0003789733,0.0003167696,0.003928586],"genre_scores_gemma":[0.9742308,0.0001642169,0.02488701,0.00004689796,0.00002778729,0.0001269017,0.000295719,0.00003502387,0.0001857362],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9319792,"threshold_uncertainty_score":0.3597327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2134094557378299,"score_gpt":0.4190955226912946,"score_spread":0.2056860669534647,"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."}}