summary.bsgw: Summarizing Bayesian Survival Generalized Weibull (BSGW) model fits

Description

summary method for class "bsgw".

Usage

# S3 method for bsgw
summary(object, pval = 0.05, burnin = object$control$burnin, ...)
# S3 method for summary.bsgw
print(x, ...)

Value

The function summary.bsgw calculates median as well as lower/upper bounds for all model coefficients, given the supplied p-value. It also calculates the p-value for coefficients being significant smaller/larger than zero. It contains returns an object of class "summary.bsgw" with the following elements:

call: The matched call.
pval: Same as input.
burnin: Same as input.
coefficients: A p x 4 matrix with columns for the estimated coefficient median, its lower and upper bounds given the user-supplied p-value, and the p-value for being smaller/larger than zero.
survreg.scale: List of lower, median, and upper values of the survreg-style scale parameter (i.e. inverse of shape parameter in rweibull) for the training-set population.

Arguments

object: An object of class "bsgw", usually the result of a call to bsgw.
x: An object of class "summary.bsgw", usually the result of a call to summary.bsgw.
pval: Desired p-value, based on which lower/upper bounds will be calculated. Default is 0.05.
burnin: Number of samples to discard from the beginning of each MCMC chain before calculating median and lower/upper bounds.
...: Further arguments to be passed to/from other methods.

Author

Alireza S. Mahani, Mansour T.A. Sharabiani

Examples

Run this code

library("survival")
data(ovarian)
est <- bsgw(Surv(futime, fustat) ~ ecog.ps + rx, ovarian
            , control=bsgw.control(iter=400, nskip=100))
summary(est, pval=0.1)