AISM 53, 203-216
© 2001 ISM

On the proportional odds model in survival analysis

S.N.U.A. Kirmani1 and Ramesh C. Gupta2

1Department of Mathematics, University of Northern Iowa, Cedar Falls, IA 50614-0506, U.S.A.
2Department of Mathematics & Statistics, University of Maine, Orono, ME 04469-5752, U.S.A.

(Received June 8, 1998; revised February 14, 2000)

Abstract.    The proportional odds (PO) model with its property of convergent hazard functions is of considerable value in modeling survival data with non-proportional hazards. This paper explores the structure, implications, and properties of the PO model. Results proved include connections with geometric minima and maxima, ageing characteristics, and bounds on mean and variance of survival times.

Key words and phrases:    Ageing characteristics, geometric distribution, random minima and maxima, residual life, stochastic orders, survival models.

Source ( TeX , DVI )