The PHREG Procedure |
For a Cox model, the model parameters are the regression coefficients. For a piecewise exponential model, the model parameters consist of the regression coefficients and the hazards or log-hazards. The priors for the hazards and the priors for the regression coefficients are assumed to be independent, while you can have a joint multivariate normal prior for the log-hazards and the regression coefficients.
Let be the constant baseline hazards.
The joint prior density is given by
This prior is improper (nonintegrable), but the posterior distribution is proper as long as there is at least one event time in each of the constant hazard intervals.
The joint prior density is given by
This prior is improper (nonintegrable), but the posteriors are proper as long as there is at least one event time in each of the constant hazard intervals.
The gamma distribution has a pdf
where is the shape parameter and is the scale parameter. The mean is and the variance is .
Suppose for , has an independent prior. The joint prior density is given by
are correlated as follows:
The joint prior density is given by
Write .
The joint prior density is given by
Note that the uniform prior for the log-hazards is the same as the improper prior for the hazards.
Assume has a multivariate normal prior with mean vector and covariance matrix . The joint prior density is given by
Let be the vector of regression coefficients.
The joint prior density is given by
This prior is improper, but the posterior distributions for are proper.
Assume has a multivariate normal prior with mean vector and covariance matrix . The joint prior density is given by
Assume has a multivariate normal prior with mean vector and covariance matrix . The joint prior density is given by
Copyright © 2009 by SAS Institute Inc., Cary, NC, USA. All rights reserved.