{"id":"W4403764486","doi":"10.1080/02664763.2024.2418473","title":"Evaluating the median <i>p</i> -value method for assessing the statistical significance of tests when using multiple imputation","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Mathematics; Wilcoxon signed-rank test; Test statistic; Statistical significance; Statistic; Statistical hypothesis testing; Logistic regression; Student's t-test; p-value; F-test; Type I and type II errors; Pearson's chi-squared test; Linear regression; Pooling; Nominal level; Imputation (statistics); Missing data; Mann–Whitney U test; Computer science; Artificial intelligence","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"],"consensus_categories":[],"category_scores_codex":[0.006115422,0.0002170528,0.0005150457,0.0000906363,0.0002393984,0.0002412564,0.000340974,0.00008574563,0.00003779274],"category_scores_gemma":[0.01086547,0.0001224119,0.00009774875,0.0002368263,0.000240447,0.00009955942,0.00004795143,0.000493566,0.000001056462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001045725,"about_ca_system_score_gemma":0.0005952651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001871131,"about_ca_topic_score_gemma":0.000006151613,"domain_scores_codex":[0.9969193,0.0004733445,0.001287121,0.0002207804,0.0007920646,0.0003074388],"domain_scores_gemma":[0.9383285,0.06001187,0.00081761,0.0002239024,0.0005237013,0.000094416],"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":[0.0000729252,0.00004421555,0.00001347288,0.000466994,0.0001089707,0.0000107468,0.001330186,0.0007686965,0.009293893,0.7125089,0.001318628,0.2740624],"study_design_scores_gemma":[0.0002228674,0.000127788,0.00007048162,0.0001244226,0.000339802,0.0000272342,0.0004021252,0.4334545,0.0006542894,0.5644193,0.0000712,0.00008601364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008742948,0.00007496119,0.9969168,0.0003097985,0.0004594193,0.0006064738,0.0006199327,0.00001543722,0.0001228347],"genre_scores_gemma":[0.07756226,0.000006557225,0.9219395,0.0000900611,0.0003208379,0.00002329032,0.000006434761,0.00004501278,0.000006063278],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4326858,"threshold_uncertainty_score":0.9974664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1524259777304091,"score_gpt":0.5050042235663473,"score_spread":0.3525782458359382,"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."}}