In this article, we present a brief non-statistical guide for clinical investigators on how to perform, interpret, and report interaction (or subgroup) analyses in RCTs.

When the treatment effect on the outcome of interest differs according to the presence (or absence) of a baseline/demographic factor, investigators say that an interaction is present. In randomized clinical trials (RCTs), statistical analysis of such a phenomenon is typically referred to as a subgroup analysis.

The reason that motivates interaction (or subgroup) analysis in RCTs is to learn how to use the treatment most effectively by identifying subgroups of patients who would and those who would not benefit from treatment, or to learn whether treatment would be harmful in specific subgroups defined by the baseline/demographic factor.

This article provides an overview of the key points of an interaction analysis including the estimation of both additive and multiplicative interaction effects. Although we have focused on the reporting of RCTs, many of the key points discussed apply equally to observational studies.

To find out more about an interaction (or subgroup) analysis in RCTs you can click here.