MATH-605. STATISTICS SEMINAR. DEPARTMENT OF MATHEMATICAL SCIENCES.

DATE:	Thurday, September 11, 2008.
TIME:	1:15 pm. to 2:40 pm.
PLACE:	LN 2205.
SPEAKER:	Tinghui Yu, Binghamton University.
TITLE:	Efficient experimental design and nonparametric modeling: with applications to the analysis of joint effects of Trimetrexate Combined with AG2034

Abstract

The design and analysis of drug combination continue to be an area requiring further methodological developments. It is highly desirable to discover those dose combinations having a synergy effect. Faessel et al. (1998) studied the joint effects of the combinations of trimetrexate (TMQ) and the GRAFT inhibitor AG2034 to inhibit the growth of HCT-8 human ileocecal adenocarcinoma cells. Their experiments provide a rich data resource to validate the performance of new experimental design and analysis methods for future experiments. We first re-analyze the same data with a nonparametric model by using a thin plate spline regression model. And we briefly review the experimental design used in the original paper. We then suggest the maximum power experimental design based on uniform measures to improve the efficiency of the experiments. Simulation results support the usage of the proposed maximum power experimental design.

Tinghui Yu (joint work with H. Fang and M. Tan from the Greenebaum Cancer Center of University of Maryland at Baltimore).

Back to the Statistics Seminar webpage.