Count data, rates, rate differences, and rate ratios in meta-analysis: A tutorial

Abstract

This tutorial focuses on trials that assess outcomes by counting events that can occur zero, one, or more than one time in each participant. Trials and meta-analyses can estimate treatment effects for count outcomes using rate differences or rate ratios. We explain why it may be appropriate to meta-analyze count data to estimate rate ratios rather than odds ratios, risk ratios, or risk differences. We explain what count data are, how trials may estimate treatment effects, how to interpret such estimates, and how to extract data from trials that use count outcomes for meta-analysis. Finally, we discuss some common misunderstandings and subtleties. Supplementary materials include an Excel file for performing calculations, mathematical background, and additional advice.