Highly-Structured Statistical Models in High-Energy Astrophysics

In recent years, an innovative trend has been growing in applied statistics—it is becoming ever more feasible to build application-specific models which are designed to account for the hierarchical and latent structures inherent in any particular data generation mechanism. Such highly-structured models have long been advocated on theoretical grounds, but recently the development of new computational tools (e.g., hardware, software, and algorithms) for statistical analysis has begun to bring such model fitting into routine practice. In this paper, we describe these methods in the context of empirical high-energy astrophysics. A new generation of scientific instruments such as the Chandra X-ray Observatory are opening a whole new window to the study of the cosmos. Unlocking the information in the data generated with these complex high-tech instruments, however, requires sophisticated statistical models, methods, and computation. Here we discuss the techniques that the California-Harvard AstroStatistics Collaboration have been using to develop application-specific highlystructured statistical models to address these problems in high-energy astrophysics.