Simulation shows multiple imputation at the DAH component level controls type I error and maintains power better than imputation at the composite level for Mann-Whitney-Wilcoxon analysis.
Multiple imputation of missing covariates with non-linear effects and interactions: an evaluation of statistical methods
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ME 2years
2026 2roles
background 1polarities
background 1representative citing papers
In a case study using EHR data from two health systems, multiple imputation via CART for missing systolic blood pressure and HbA1c values showed that marginal versus conditional imputation affected imputed distributions but had minimal impact on inferences about neighborhood socioeconomic status and
citing papers explorer
-
Component over Composite: Mitigating Type I Error Inflation when Imputing "Days Alive and at Home"
Simulation shows multiple imputation at the DAH component level controls type I error and maintains power better than imputation at the composite level for Mann-Whitney-Wilcoxon analysis.
-
Multiple Imputation Diagnostics when using Electronic Health Record Data in Observational Studies: A Case Study
In a case study using EHR data from two health systems, multiple imputation via CART for missing systolic blood pressure and HbA1c values showed that marginal versus conditional imputation affected imputed distributions but had minimal impact on inferences about neighborhood socioeconomic status and