Modelling accelerated failure time with a Dirichlet process
Ronald Christensen, Wesley O. Johnson · Biometrika · 1988
The relationship between survival times and covariates is modelled via the accelerated failure time model with a Dirichlet process prior assumed for the underlying baseline survival function. Emphasis is placed on estimating the survival distribution for future individuals with given covariates. A method of estimating regression coefficients which uses the marginal distribution for observed censored data is given. The proposed procedures are shown to perform reasonably on two artificial data sets, and an analysis of the Stanford heart transplant data is given.