summary_BayesMixSurv: Summarizing BayesMixSurv model fits

In BayesMixSurv: Bayesian Mixture Survival Models using Additive Mixture-of-Weibull Hazards, with Lasso Shrinkage and Stratification

Description

summary method for class "bayesmixsurv".

Usage

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

Arguments

object	An object of class 'bayesmixsurv', usually the result of a call to bayesmixsurv.
x	An object of class "summary.bayesmixsurv", usually the result of a call to summary.bayesmixsurv.
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.

Value

An object of class summary.bayesmixsurv, with the following elements:

call	The matched call.
pval	Same as input.
burnin	Same as input.
single	Copied from object$control$single. See bayesmixsurv.control for explanation.
coefficients	A list including matrices alpha, beta1, beta2, and gamma (if stratification is used). Each matrix has columns named 'Estimate', 'Lower Bound', 'Upper Bound', and 'P-val'. alpha has two rows, one for each components, while each of beta1 and beta2 has one row per covariate. gamma has one row per stratum (except for the reference stratum).

Author(s)

Alireza S. Mahani, Mansour T.A. Sharabiani

See Also

See summary for a description of the generic method.

The model fitting function is bayesmixsurv.

Examples

est <- bayesmixsurv(Surv(futime, fustat) ~ ecog.ps + rx, ovarian
            , control=bayesmixsurv.control(iter=800, nskip=100))
summary(est, pval=0.1)

Example output

Loading required package: survival
BayesMixSurv 0.9.1
Bayesian Mixture-of-Weibull Survival model for right-censored data.
finished sample 100 of 800 
finished sample 200 of 800 
finished sample 300 of 800 
finished sample 400 of 800 
finished sample 500 of 800 
finished sample 600 of 800 
finished sample 700 of 800 
finished sample 800 of 800 
Call:
bayesmixsurv(formula1 = Surv(futime, fustat) ~ ecog.ps + rx, 
    data = ovarian, control = bayesmixsurv.control(iter = 800, 
        nskip = 100))
number of burn-in iterations discarded: 400 
confidence interval: 0.1 
## shape coefficients ##
        Estimate Lower Bound Upper Bound  P-val
alpha1 0.7507229  0.08372819   0.9719668 0.0025
alpha2 1.1531651  1.01279304   1.4568134 0.0025
## scale coefficients ##
component 1:
               Estimate Lower Bound Upper Bound P-val
(Intercept) -5.17806500   -9.469228 -0.05020434 0.090
ecog.ps     -0.01548622   -3.057210  1.45321848 0.985
rx          -0.57113991   -3.162437  0.71528337 0.455
component2:
             Estimate Lower Bound Upper Bound P-val
(Intercept) -2.986097   -9.508068   0.4481478 0.250
ecog.ps     -1.209920   -6.330863   0.9636039 0.535
rx          -1.741759   -7.363070   0.1671934 0.215

BayesMixSurv documentation built on May 1, 2019, 7 p.m.