Reproducibility vs. Replication

Dave Giles recently reminded us of the distinction between replication and reproducibility:

We might be inclined to use the terms “replicate” and “reproduce” interchangeably. However, in the context of scientific verification, a distinction has been drawn between them.

He pointed to a post by Roger Peng who succinctly described the distinction as follows:

As I made clear in the commentary, I define “replication” as independent people going out and collecting new data and “reproducibility” as independent people analyzing the same data.

In a separate post, Peng made the important point that while reproducibility can indeed help facilitate the transfer of knowledge, it does not, on its own, speak to the validity of the analysis. It does, however, make checking the validity easier if the steps taken are obvious due to the research being easily reproducible.

For further reading, I’ve updated my Reproducibility in Economics page with links to a series of other articles by Peng on reproducibility and replication as well as several journal articles and posts by other authors.