I offer a two-day summer course on propensity scores through the Johns Hopkins Bloomberg School of Public Health (JHSPH) Department of Mental Health Summer Institute. In the summer of 2009 this course may instead be replaced by a course on missing data; check back for details!
I also teach a third-term class at JHSPH on causal inference in medicine and public health. It is targeted towards 3rd or 4th year PhD students from across the school who are interested in learning the basic designs for estimating causal effects, with a focus on non-experimental studies. More information can be found here.
In the Spring of 2006 I taught a graduate-level course on causal inference in observational studies and randomized experiments as an adjunct faculty member at the Joint Program in Survey Methodology (University of Maryland).
I also had extensive teaching experience while at Harvard. In particular, I was the Teaching Fellow for Stat 214 (Causal Inference in Statistics and the Social and Biomedical Sciences) for two years, and was very involved in the development of a version of that course for students with little or no technical background, QR 33 (Causal Inference), which has now been taught for three years. A summary of my Harvard teaching evaluations can be found here.
I have also taught short courses on "Causal inference through the use of potential outcomes", with Donald Rubin and Samantha Cook. These have been taught at the University of Wisconsin Medical College, the University of Minnesota, Harvard University, Smith College, the Joint Statistical Meetings, the Food and Drug Administration, and the Karolinska Institute in Stockholm, Sweden.