| coxlps.baseline {blapsr} | R Documentation |
Extract estimated baseline quantities from a fit with coxlps.
Description
The routine takes as input an object of class 'coxlps' and computes point estimates and credible intervals for the baseline hazard and survival on a user-specified time vector.
Usage
coxlps.baseline(object, time = NULL, compute.cred = TRUE, cred.int = 0.95,
verbose = TRUE)
Arguments
object |
An object of class 'coxlps'. |
time |
A vector of time values on which to compute the estimated baseline quantities. Each component of 'time' must be between 0 and the largest observed follow-up time. If time is 'NULL' (the default), then only the baseline median lifetime (if available) is computed. |
compute.cred |
Should the credible intervals be computed? Default is TRUE. |
cred.int |
The level for an approximate pointwise credible interval to be computed for the baseline hazard and survival curves. Default is 0.95. |
verbose |
Should the table of estimated values be printed to console? Default is TRUE. |
Value
A list with the following components:
fit.time |
A matrix with point and set estimates of the baseline hazard and survival curves for values provided in 'time'. Only available if 'time' is not 'NULL'. Column Time summarizes the provided values in 'time'. Columns named h0, S0, are the point estimates of the baseline hazard and baseline survival respectively. low and up give the lower and upper bound respectively of the approximate pointwise credible interval. |
median.lifetime |
The estimated baseline median lifetime. |
cred.int |
The chosen level to construct credible intervals. |
Author(s)
Oswaldo Gressani oswaldo_gressani@hotmail.fr.
Examples
## Simulate survival data
set.seed(2)
betas <- c(0.15, 0.82, 0.41) # Regression coefficients
data <- simsurvdata(a = 1.8, b = 2, n = 300, betas = betas, censperc = 15)
simdat <- data$survdata
# Fit model
fit <- coxlps(Surv(time, delta) ~ x1 + x2 + x3, data = simdat, K = 20)
coxlps.baseline(fit, time = seq(0, 2, by = 0.5), cred.int = 0.90)