Replicability and Meta-Analysis

In this chapter, I will discuss statistical considerations for studying repli cation. More specifically, I will approach replication from a framework based on meta-analysis. To do so, I will focus on direct replications, where studies are designed to be as similar as possible, as opposed to conceptual replications that (systematically or haphazardly) vary in at least one aspect of an experiment. The chapter starts with a brief description of recent research on replication in psychol ogy and uses examples from that research to highlight relevant considerations in defining and parametrizing “replication.” It then outlines different ways to frame analyses of replication and provides examples. Finally, it takes one possible defini tion of replication—that effects found across studies involving the same phenome non are consistent—and describes relevant analyses and their properties.