A bias test for heteroscedastic linear least-squares regression

TL;DR

This paper introduces a simple bias test for heteroscedastic linear least-squares regression, addressing issues like omitted variables and measurement errors, validated through simulations and real data applications.

Contribution

It proposes a novel, straightforward bias detection test specifically designed for heteroscedastic linear regression models, filling a gap in existing diagnostic tools.

Findings

The bias test effectively detects bias in simulated data.

Application to real datasets demonstrates practical utility.

The method outperforms some existing bias detection techniques.

Abstract

Linear least squares regression is subject to bias due to an omitted variable, a mismeasured regressor, or simultaneity. A simple test to detect the bias is proposed and explored in simulation and in real data sets.