Accounting for Expected Adjusted Effect

Kimmo Sorjonen; Bo Melin; Michael Ingre

doi:10.3389/fpsyg.2020.542082

Accounting for Expected Adjusted Effect

Front Psychol. 2020 Sep 17:11:542082. doi: 10.3389/fpsyg.2020.542082. eCollection 2020.

Authors

Kimmo Sorjonen¹, Bo Melin¹, Michael Ingre^{1

2

3}

Affiliations

¹ Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
² Department of Psychology, Faculty of Social Sciences, Stockholm University, Stockholm, Sweden.
³ Institute for Globally Distributed Open Research and Education (IGDORE), Stockholm, Sweden.

Abstract

The point that adjustment for confounders do not always guarantee protection against spurious findings and type 1-errors has been made before. The present simulation study indicates that for traditional regression methods, this risk is accentuated by a large sample size, low reliability in the measurement of the confounder, and high reliability in the measurement of the predictor and the outcome. However, this risk might be attenuated by calculating the expected adjusted effect, or the required reliability in the measurement of the possible confounder, with equations presented in the present paper.

Keywords: adjustment; confounder; expected effect; regression analysis; reliability; simulation; type 1-error.