|
Summary of research interests
Dr. Hunter's main interests lie in the theory and
application of computational algorithms in statistics.
His work on MM algorithms, which generalize the well-known
class of EM algorithms, demonstrates the wide applicability
of these algorithms in diverse statistical situations.
Other work involves the statistical modeling of social
network data. Specifically, Dr. Hunter works on developing
probability models that concisely and accurately describe
observed patterns of relationships as functions of network
statistics, as well computational methods for the arduous
task of maximum likelihood estimation in these models.
Finally, Dr. Hunter works on theoretical and computational
tools for estimation in certain types of mixture models.
Mixture models arise when data are believed to come
from several distinct groups, but group membership is
not part of the data.
Representative publications
Hunter DR, Wang S, and Hettmansperger TP. 2005. Inference
for mixtures of symmetric distributions. Annals
of Statistics (to appear).
Hunter DR and Handcock MS. 2005. Inference in curved
exponential family models for networks. Journal
of Computational and Graphical Statistics (to appear).
Hunter DR and Li R. 2005. Variable selection using
MM algorithms. Annals of Statistics (to appear).
Hunter DR and Lange K. 2004. A Tutorial on MM Algorithms.
The American Statistician 58: 30-37.
Hunter DR. 2004. MM algorithms for generalized Bradley-Terry
models. Annals of Statistics 32: 386-408.
K. Lange, D. R. Hunter, and I. Yang. 2000. Optimization
transfer using surrogate objective functions. Journal
of Computational and Graphical Statistics 9: 1-59.
Last updated: 26 April
2005
|
Associate
Professor of Statistics
