|
Organizers |
Theory and Applications of Bivariate Weibull Multiple Regression in Biological and Physical Systems
by
Yi Han
Department of Mathematics and Statistics, Auburn University
Coauthors: Mark Carpenter and Norou Diawara, Department of Mathematics and Statistics, Auburn University
In this paper, we review the literature to-date on bivarite survival and reliability models, i.e., positive support distributions, and propose a new bivariate Weibull regression model. The new model is characterized and maximum likelihood estimators (MLE) are developed. The joint MLE shown to have optimal properties over the marginal MLE ("working independence" assumption) when the underlying distribution is Weibull. Because of the flexibility of the Weibull distribution, this new model also produces efficient estimators of the regression coefficients even when the underlying distribution is bivarite Normal.
Date received: September 23, 2005
Copyright © 2005 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # caqt-87.