Article of the Week

The article of the week this week is “Damned if you do, damned if you don’t: subgroup analysis and equity.” The authors discuss the problems with and potential benefits of subgroup analysis in trials. This topic was hotly debated at a conference on population health intervention research I attended last year. Overall I have to say that I’m not really a fan of subgroup analysis for making inferences about intervention effects. The authors sum up the reasons why nicely. One thing the authors don’t really talk about is using subgroup analysis to test for the homogeneity of effect (aka. constant effect) assumption in a randomized controlled trial. This is an important assumption for making causal claims related to the population average treatment effect (ATE) rather than the average treatment effect on the treated. Perhaps I’ll write a reply to JECH?

Submit a Comment

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>