Correlation or regression, that’s the question

European Journal of Endocrinology, vol. 184, pp. E15–E18

Abstract

There are different ways to quantify the relation between two or more continuous variables. Some researchers use correlation coefficients; others will apply regression methods such as linear regression. In this paper, we show that the choice between correlation and regression is not purely a statistical one but largely depends on the research aims. Importantly, one should always inspect the data before using either of the two methods.

Authors 3

1. Saskia le Cessie corresponding Aachen 1Department of Clinical Epidemiology 2Department of Biomedical Data Sciences

   Leiden University Medical Center

   Affiliation as printed

   1Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands

   2Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands

2. Rolf H. H. Groenwold Aachen 1Department of Clinical Epidemiology 2Department of Biomedical Data Sciences

   Leiden University Medical Center

   Affiliation as printed

   1Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands

   2Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands

3. Olaf M. Dekkers Aachen 1Department of Clinical Epidemiology 3Department of Endocrinology

   Leiden University Medical Center

   Affiliation as printed

   1Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands

   3Department of Endocrinology, Leiden University Medical Center, Leiden, The Netherlands