groupedSurv (version 1.0.5.1)

betaEst: Estimate the Parameter of Interest for the Grouped Survival Model

Description

A method to estimate the parameter of interest given the baseline survival rates for each time interval and optional covariate nuisance parameters for a grouped survival model. The function supports zero, single, or multiple covariates as dictated by the input data.

Usage

betaEst(x, Z=NULL, alpha, theta=NULL, gtime, delta)

Value

Scalar estimate of the parameter of interest.

Arguments

x

Vector of numeric variable of interest for each sample.

Z

Optional data.frame or matrix of numeric covariate values for each sample.

alpha

Vector of baseline survival rates for each time interval.

theta

Optional vector of estimated nuisance parameters for the covariates.

gtime

Vector of observed survival times for each sample.

delta

Vector of event indicators for each sample: 1 indicates observed event, 0 indicates censored.

Examples

# Generate dummy data	
x     <- c(1, 0, 1, 1, 1, 0, 1, 0, 1)
cov1  <- c(1, 2, 2, 2, 1, 1, 0, 1, 1)
cov2  <- c(2, 2, 1, 0, 1, 0, 1, 1, 0.5) 
Z     <- cbind(cov1, cov2)
gtime <- c(1, 3, 3, 2, 1, 1, 2, 3, 1)
delta <- c(1, 0, 1, 1, 1, 0, 1, 0, 1)

#theta <- thetaEst(Z, gtime, delta) 

#res   <- betaEst(x, Z, theta$alpha, theta$theta, gtime, delta) 
#res