Log-logistic accelerated-failure-time model — morie_aft_log

\(\log T = x'\beta + \sigma W\) with W standard logistic. The hazard rises then falls, which is what recommends it when the risk peaks early and then recedes – a shape no proportional-hazards Weibull can produce.

Usage

morie_aft_log_logistic(time, event, X, ...)

Arguments

time: follow-up times, strictly positive.
event: 1 for an event, 0 for right-censored.
X: covariate matrix, one row per subject. An intercept is added.
...: passed to the fitter (max_iter, tol, add_intercept).

Value

as morie_aft_weibull.

Details

As for every AFT model, exp(beta) is a time ratio: positive means longer survival.

References

Bennett, S. (1983). Log-logistic regression models for survival data. Applied Statistics, 32(2), 165-171.

Examples

set.seed(2)
X <- matrix(rnorm(200), ncol = 2)
tt <- exp(0.5 + X %*% c(0.8, -0.4) + 0.6 * rlogis(100))
round(morie_aft_log_logistic(tt, rep(1, 100), X)$sigma, 3)
#> [1] 0.653