Flexible Statistical Modeling

Stanford University, Stanford CA

Investigators

Abstract

The investigator studies statistical models in a variety of applied situations which require innovative modifications of the standard technology. Document classification builds models in extremely high-dimensional feature spaces, as do models for inference and prediction with gene expression arrays. Species occurrence and abundance models deal with large numbers of species, often sharing many characteristics. In each of these settings, the different contexts have led the researcher to develop special forms of regularization that allow one to exploit the structure in the data. In this advanced technological age, we are faced with analyzing extremely large volumes of data. Two of the several examples this researcher deals with are gene expression measurements (40 thousand measurements per human sample), and online document classification (often the web is the source). Standard statistical tools do not work well in these situations. This investigator studies innovative adaptations of these tools designed to defeat the challenges these problems pose.