Patrick Vu | Why are replication rates so low?
Seminar talk
Topic
Why Are Replication Rates So Low?
Many explanations have been offered for why replication rates are low in the social sciences, including selective publication, p-hacking, and treatment effect heterogeneity. This article emphasizes that issues with the most commonly used approach for setting sample sizes in replication studies may also play an important role. Theoretically, I show in a simple model of the publication process that we should expect the replication rate to fall below its nominal target, even when original studies are unbiased. The main mechanism is that the most commonly used approach for setting the replication sample size does not account for non-linearities in the replication power function. Empirically, I find that a parsimonious model accounting only for these issues can fully explain observed replication rates in experimental economics and social science, and two-thirds of the replication gap in psychology. I conclude with practical recommendations for replicators.
Expression of interest
About the speaker
Patrick Vu is an Assistant Professor/Lecturer of Economics at the UNSW Business School.
His research interests are primarily in applied and theoretical econometrics, with a focus on how publication bias impacts the statistical credibility of published research and the quality of evidence-based policy decisions.
He received his PhD in economics at Brown University, where he was awarded the George Borts Prize for best dissertation. He holds an MPhil in economics from the University of Oxford and an undergraduate degree from the University of Western Australia, with majors in economics and classical music.
Learn more about him on his personal website.