Multiple Imputation Through XGBoost

TL;DR

This paper introduces mixgb, a scalable multiple imputation framework using XGBoost that efficiently handles large, complex datasets by capturing non-linear relations and interactions, improving imputation accuracy and computational speed.

Contribution

The paper presents a novel MI framework based on XGBoost, combining subsampling and predictive mean matching for improved scalability and performance on large datasets.

Findings

Effective handling of large datasets with complex structures

High computational efficiency achieved by XGBoost-based imputation

Reduced bias through subsampling and predictive mean matching

Abstract

The use of multiple imputation (MI) is becoming increasingly popular for addressing missing data. Although some conventional MI approaches have been well studied and have shown empirical validity, they have limitations when processing large datasets with complex data structures. Their imputation performances usually rely on the proper specification of imputation models, which requires expert knowledge of the inherent relations among variables. Moreover, these standard approaches tend to be computationally inefficient for medium and large datasets. In this paper, we propose a scalable MI framework mixgb, which is based on XGBoost, subsampling, and predictive mean matching. Our approach leverages the power of XGBoost, a fast implementation of gradient boosted trees, to automatically capture interactions and non-linear relations while achieving high computational efficiency. In addition, we incorporate subsampling and predictive mean matching to reduce bias and better account for appropriate imputation variability. The proposed framework is implemented in an R package mixgb. Supplementary materials for this article are available online.