Pitfalls in testing with linear regression model by OLS

TL;DR

This paper critically examines the testing procedures in linear regression models by OLS, highlighting methodological issues that may affect the validity of previous conclusions.

Contribution

It identifies specific pitfalls in testing with linear regression models that can lead to altered interpretations of results.

Findings

Methodological issues can bias test outcomes

Certain assumptions in OLS testing may be violated

Revised testing approaches improve accuracy

Abstract

This is a comment on Economic Letters DOI http://dx.doi.org/10.1016/j.econlet.2015.10.015. We show that due to some methodological aspects the main conclusions of the above mentioned paper should be a little bit altered.