weibull_scale: Estimate Scale for Weibull Accelerated Failure Time Model

In lgspline: Lagrangian Multiplier Smoothing Splines for Smooth Function Estimation

Estimate Scale for Weibull Accelerated Failure Time Model

Description

Computes maximum log-likelihood scale estimate of Weibull accelerated failure time (AFT) survival model.

This both provides a tool for actually fitting Weibull AFT Models, and boilerplate code for users who wish to incorporate Lagrangian multiplier smoothing splines into their own custom models.

Usage

weibull_scale(log_y, log_mu, status, weights = 1)

Arguments

log_y	Logarithm of response/survival times
log_mu	Logarithm of predicted survival times
status	Censoring indicator (1 = event, 0 = censored) Indicates whether an event of interest occurred (1) or the observation was right-censored (0). In survival analysis, right-censoring occurs when the full survival time is unknown, typically because the study ended or the subject was lost to follow-up before the event of interest occurred.
weights	Optional observation weights (default = 1)

Details

Calculates maximum log-likelihood estimate of scale for Weibull AFT model accounting for right-censored observations using Brent's method for optimization.

Value

Scalar representing the estimated scale

Examples

## Simulate exponential data with censoring
set.seed(1234)
mu <- 2  # mean of exponential distribution
n <- 500
y <- rexp(n, rate = 1/mu)

## Introduce censoring (25% of observations)
status <- rbinom(n, 1, 0.75)
y_obs <- ifelse(status, y, NA)

## Compute scale estimate
scale_est <- weibull_scale(
  log_y = log(y_obs[!is.na(y_obs)]),
  log_mu = log(mu),
  status = status[!is.na(y_obs)]
)

print(scale_est)

lgspline documentation built on June 8, 2025, 10:45 a.m.