mixgb: Multiple Imputation Through XGBoost

Multiple imputation is increasingly used in dealing with missing data. While some conventional multiple imputation approaches are well studied and have shown empirical validity, they entail limitations in processing large datasets with complex data structure. In this talk, we will introduce our R package mixgb​, which implements a scalable multiple imputation framework based on XGBoost, bootstrapping, and predictive mean matching. We will also demonstrate some visual diagnostic functions for inspecting multiply imputed values for incomplete variables.

Jul 6, 2021 1:30 PM — 3:10 PM