On the Relation between Prediction and Imputation Accuracy under Missing Covariates

TL;DR

This paper investigates how the accuracy of imputing missing covariates affects the prediction performance in regression tasks, using simulations and empirical datasets to analyze the interplay between imputation and prediction accuracy.

Contribution

It provides a comprehensive analysis of the relationship between imputation and prediction accuracy in regression with missing data, including the impact on prediction intervals and statistical inference.

Findings

Imputation accuracy significantly influences prediction performance.

Machine Learning-based imputation methods improve prediction accuracy.

Coverage rates of prediction intervals are affected by imputation quality.

Abstract

Missing covariates in regression or classification problems can prohibit the direct use of advanced tools for further analysis. Recent research has realized an increasing trend towards the usage of modern Machine Learning algorithms for imputation. It originates from their capability of showing favourable prediction accuracy in different learning problems. In this work, we analyze through simulation the interaction between imputation accuracy and prediction accuracy in regression learning problems with missing covariates when Machine Learning based methods for both, imputation and prediction are used. In addition, we explore imputation performance when using statistical inference procedures in prediction settings, such as coverage rates of (valid) prediction intervals. Our analysis is based on empirical datasets provided by the UCI Machine Learning repository and an extensive simulation study.