Department of Statistics Seminar
North Carolina State University

Bruce Weir, Jeffrey Thorne,
Sujit Ghosh, and David Dickey

Four members of the Department of Statistics at NCSU will present brief overviews of their current research.

Bruce Weir - "Using Statistics to Find Genes"
The Program in Statistical Genetics has several projects underway to locate the genes affecting discrete or continuous characters on the basis of observed patterns of "marker" genes that have a known location in the genome.
Jeffrey Thorne - "Combining Protein Structure and Protein Evolution"
Protein sequence evolution is constrained so as to maintain protein structure. Statistical approaches for studying evolution and for predicting protein structure from groups of related protein sequences can exploit this fact.
Sujit Ghosh - "Spatial Modeling: A Bayesian Approach"
Spatial modeling is a relatively new development within Bayesian statistics. We begin by making some general comments on the types of spatio-temporal systems which we shall, and shall not, be discussing. It is maintained throughout that the conditional probability approach to the specification and analysis of spatial interaction is more attractive than the alternative joint probability approach.
David Dickey - "Stationarity Testing"
An important part of time series analysis is deciding whether or not the series is stationary (mean reverting). Our work provides a formal hypothesis test based on a regression estimator that is not normal or chi-square even in the limit.

Refreshments will be served on the second floor of Dabney Hall (left of Room 222) at 3:00 pm.