The Reasoned Evidence from Difficult Data Initiative. From 2013 (heck it was the International Year of Statistics after all), I've been aiming to be more galvanized and thematic in my research program. More and more, I'm drawn to questions of how much useful information can be extracted from difficult data. Roughly put, REDDI is where Bayesian inference meets partial identification meets causal inference. Having trouble remembering the snazzy acronym? Just think: the difficult data are coming, we'd better be REDDI.
I'm fortunate to work and have worked with many current and former graduate students and postdoctoral fellows.
You can check out recent courses on my teaching page. I taught part of STAT 536 in the Spring 2015 term. This is a survey course of biostatistical topics.
If you do take a course with me, there will almost certainly be some `active learning' components (see CWSEI for thoughts on this, and other issues around effective science education). For a completely different take on statistics eduction, I'd recommend the story segment of the April 13, 2013 Vinyl Cafe episode.
My research page includes preprints as well as published work, and links to code and supplementary materials. Or you can check my profile on Google Scholar.
Currently I am the Statistical Editor for Epidemiology, and an Associate Editor for the Journal of the American Statistical Association (Applications & Case Studies Section).
At the 2014 Atlantic Causal Inference Conference (May 15-16, Providence), at Bayesian Biostatistics 2014 (July 2-5, Zurich), and at IBC 2014 (July 6-11, Florence).