http://www.ncbi.nlm.nih.gov/pubmed/1271224, via this article on bathroom behavior in the Atlantic.
I attended this several years ago, and it is an excellent training opportunity: 2014 Summer Research Training Institute on Cluster-Randomized Trials
As someone who serves on four ed boards, I found this presentation very interesting: How can We Increase Pro-Social Behavior? An Experiment with Referees at the Journal of Public Economics Referees randomized to one of four groups in invitation emails: 1. 6 week – 6 week deadline [control group] 2. Social – 6 week deadline…
A colleague at NCSU asked my opinion of this paper, which tests the effect of a diversity education intervention on GPA. In general, the paper is quite detailed and the analysis carefully done. But the authors find that their intervention has quite an impact: This main effect was qualified, however, by the predicted interaction of…
Mike Bastedo sent this to me; it’s a field experiment looking at how faculty respond to email requests from prospective doctoral students of different races and gender. Their Figure 2 is pretty amazing; I would not have guessed the differential was so large within the field of education (although note the size of the standard…
“In other words, discovering program improvements that really work is extremely hard. We labor in the dark — scratching and clawing for tiny scraps of causal insight.” On Megan McArdle’s blog.
And it’s not the standard, “too difficult, unethical, etc.” arguments you always hear: http://www.edge.org/response-detail/25497
My ASHE paper with Ashley Clayton reviewing field experiments from the past decade can be found here. Bear in mind that it is a very rough draft. We need to go into more detail about how randomization was accomplished, and we haven’t presented the effect sizes yet.