Department of Statistics Seminar
North Carolina State University
presents
Drs. Wenbin Lu, Jung-Ying Tzeng and Roger Woodard
North Carolina State University
A Sampler of NCSU Faculty
- Dr. Wenbin Lu lu@stat.ncsu.edu (download the slides)
Title: Semiparametric transformation models for case-cohort study
Abstract: A general class of semiparametric transformation models is studied
for analyzing survival data from the case-cohort design, which was
introduced by Prentice (1986). Weighted estimating equations are
proposed for simultaneous estimation of the regression parameters
and the transformation function. It is shown that the resulting
regression estimators are asymptotically normal, with
variance-covariance matrix that has a closed form and can be
consistently estimated by the usual plug-in method. Simulation
studies show that the proposed approach is appropriate for
practical use.
This is joint work with Butch Tsiatis at the NC State University.
- Dr. Jung-Ying Tzeng tzeng@stat.ncsu.edu (download the slides)
Title: Cladistic Clustering of Haplotypes in Association Analysis
Abstract: Haplotypes represent underlying polymorphisms more than single SNPs,
and are considered as a more informative format of data in association
analysis. To model haplotypes, it requires high degrees of freedom,
which could decrease power and limit a model's capacity to incorporate
other complex effects such as interactions. Even within haplotype
blocks, high degrees of freedom are still a concern unless one chooses
to discard rare haplotypes. In this talk, I will talk about the
current strategies to increase the efficiency and power of haplotype
analysis, and introduce a cladistic grouping algorithm to cluster rare
haplotypes to the corresponding ancestral haplotypes
probabilistically. Through this algorithm, we perform association
analysis based on groups of haplotypes. Simulation results suggest
that performing tests on the groups of haplotypes obtained by the
algorithm can provide extra power even for blockily structured
sequences.
- Dr. Roger Woodard woodard@stat.ncsu.edu (download the slides)
Title: Using Concept Maps in Planning an Introductory Statistics Course
Abstract: Students in introductory statistics courses typically see the course
material as a series of disconnected topics. Students often learn these
topics in a piecewise fashion rather than as part of an overall topic. In
this presentation we consider a solution to this problem by using a tool
known as a concept map. Concept maps are visual representations of the
material in a course that help students understand how the topics
interrelate and see the underlying themes and common threads. Faculty and
instructors who use concept maps to plan their courses will find that they
can more successfully motivate the material. In this presentation we will
provide recommendations for constructing concept maps and point out
advantages of their use.
Friday, August 27, 2004
3:35 - 4:35 pm
206 Cox Hall
Refreshments will be served on the second floor of Dabney Hall
(left of Room 222) at 3:00 pm.