2021-2022 | Research Synthesis

Synthesizing results across multiple studies is a popular way to increase the robustness of scientific findings. The most well-known method for doing this is meta-analysis, which combines multiple studies at the level of the effect size to see whether there is evidence for an effect when all studies are taken together. However, a limitation to meta-analysis is that only studies with a common effect-size metric can be combined. Bayesian evidence synthesis is a relatively novel research synthesis method that does not combine studies at the level of the effect size, but at the level of the evidence for a given hypothesis. Therefore, Bayesian evidence synthesis does not pose any restrictions on the estimates to be combined.

In this project, I compared the performance of meta-analysis and Bayesian evidence synthesis by means of a simulation study and an empirical application. In doing so, I hope to enable researchers to make an informed decision on whether to use meta-analysis or Bayesian evidence synthesis, or both, for the purposes of their own study.