The best thing about being a statistician is that you get to play in everyone's backyard.
— John Tukey
My research interests center around making effective inferences in complex scientific problems. On the applications side, I have active collaborations in neuroscience, cosmology, astronomy, and entomology. On the theoretical side, I am interested confidence sets for nonparametric inference, adaptive function estimation, spatial statistics, inverse problems, and multiple testing.
Currently, in neuroscience, I am working with different groups to study the remapping of human's visual representation during and after eye movements and the role of the amygdala and pre-frontal cortex in depression. In cosmology and astronomy, our astrostatistics group is developing new methods for estimating the Cosmic Microwave Background spectrum, for studying the distribution of galaxy clusters, and for source detection in radio astronomy.
My recent theoretical work has focused on two threads. First, improving power in multiple problems using the False Discovery Rate or its variants. Larry Wasserman and I have devised some new techniques in this vein that I find quite exciting. The second thread is in constructing confidence sets in function estimation properties that are uniform over the target space and have finite-sample validity.
You can also take a look at my Curriculum Vitae and find some links to selected recent papers and some recent talks. [All this needs a little updating...] My Statistics Department bio page, is also available, although it is a bit dated.