R: Function to Fit the Penalized Parametric Bayesian Accelerated...
aftGL
R Documentation
Function to Fit the Penalized Parametric Bayesian Accelerated Failure Time Model with Group Lasso Prior
Description
Penalized parametric Bayesian accelerated failure time model with group lasso prior is implemented to analyze survival data with high-dimensional covariates.
a data.frame containing the time-to-event outcome, the censoring indicator, p covariate vectors from n subjects. It is of dimension n\times (p+2).
grpInx
a vector of p group indicator for each variable
hyperParams
a numeric vector containing hyperparameter values in hierarchical models: c(nu0, sigSq0, alpha0, h0, rLam, deltaLam).
(nu0, sigSq0): hyperparameters for the prior of σ^2; (alpha0, h0): hyperparameters for the prior of α; (rLam, deltaLam): hyperparameters for the prior of λ^2.
startValues
a numeric vector containing starting values for model parameters: c(alpha, beta, sigSq, tauSq, lambdaSq, w). See Examples below.
numReps
total number of scans
thin
extent of thinning
burninPerc
the proportion of burn-in
Value
aftGL returns an object of class aftGL.
Author(s)
Kyu Ha Lee, Sounak Chakraborty, (Tony) Jianguo Sun
References
Lee, K. H. (2011). Bayesian Variable Selection in Parametric and Semiparametric
High-Dimensional Survival Analysis. Ph.D. thesis, University of
Missouri–Columbia.
Lee, K. H., Chakraborty, S., and Sun, J.
Variable Selection for High-Dimensional Genomic Data with Censored Outcomes Using Group Lasso Prior. submitted.