About this blog Subscribe to this blog

Bruno: The Reproducibility of Educational Research

Referees-have-asked-Newton-to-reproduce-the-apple-gravity-experimentThere's been a lot of buzz recently for The Reproducibility Project: an effort by a group of researchers to attempt to reproduce the results of every study published in several prominent journals of psychology over the course of a year. Reproducibility is something that's underrated - and disincentivized - in science generally, so this has the potential to be important work.

The journals being covered - Journal of Personality and Social PsychologyPsychological Science, and Journal of Experimental Psychology: Learning, Memory, and Cognition - sometimes include education-related studies, but as a teacher I'd really like to see stronger reproducibility tests in educational research specifically. My experience is that a lot of studies of educational interventions have weak controls, poorly defined comparison groups, and small sample sizes. It wouldn't surprise me at all to find that a third or more of education studies failed to be reproduced by a new set of researchers.

If things go well for The Reproducibility Project, however, we might just see a market for this kind of thing spring up and spread to other fields. You can actually check out their progress as they work through the studies here. - PB (@MrPABruno) (image source)

Comments

Feed You can follow this conversation by subscribing to the comment feed for this post.

It’s funny, considering that “additional testing improves results” is essentially lesson one of any statistics course. No trial proves anything, and should only be looked at even remotely seriously if it’s been done multiple times by many different groups, with the same result.

The comments to this entry are closed.

Disclaimer: The opinions expressed in This Week In Education are strictly those of the author and do not reflect the opinions or endorsement of Scholastic, Inc.