Parametric Modal Regression with Error in Covariates

TL;DR

This paper introduces a new inference method for modal regression models with measurement error in covariates, including a diagnostic tool, demonstrated through simulations and real data.

Contribution

It proposes a novel estimation procedure and diagnostic tool for modal regression with measurement error, addressing a gap in existing methods.

Findings

The method provides consistent parameter estimates in error-prone covariate models.

The diagnostic tool effectively assesses model assumptions.

Empirical results highlight the importance of accounting for measurement error.

Abstract

An inference procedure is proposed to provide consistent estimators of parameters in a modal regression model with a covariate prone to measurement error. A score-based diagnostic tool exploiting parametric bootstrap is developed to assess adequacy of parametric assumptions imposed on the regression model. The proposed estimation method and diagnostic tool are applied to synthetic data generated from simulation experiments and data from real-world applications to demonstrate their implementation and performance. These empirical examples illustrate the importance of adequately accounting for measurement error in the error-prone covariate when inferring the association between a response and covariates based on a modal regression model that is especially suitable for skewed and heavy-tailed response data.