Nonparametric Bayesian analysis of the accelerated failure time model
The baseline probability distribution for accelerated failure time is modeled with a Dirichlet process. A fully Bayesian analysis is developed for the estimation of regression coefficients as well as for the estimation of survival curves. The practical difficulties associated with this theoretically desirable analysis are emphasized.
Year of publication: |
1989
|
---|---|
Authors: | Johnson, Wesley ; Christensen, Ronald |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 8.1989, 2, p. 179-184
|
Publisher: |
Elsevier |
Keywords: | accelerated failure time Dirichlet process empirical Bayes non-parametric Bayes semi-parametric model |
Saved in:
Saved in favorites
Similar items by person
-
A New Perspective on Priors for Generalized Linear Models
Bedrick, Edward J., (1996)
-
Johnson, Wesley, (1987)
-
Plane answers to complex questions : the theory of linear models
Christensen, Ronald, (1987)
- More ...