Movatterモバイル変換

spsurv

An R package for semi-parametric survival analysis.

Thespsurv package was designed to contribute with aflexible set of semi-parametric survival regression modelings, includingproportional hazards (PH), proportional odds (PO), and acceleratedfailure time (AFT) models for right-censored data.

• Install and load thespsurv package using the devtoolspackage.

install.packages("devtools")library(devtools)install_github("rvpanaro/spsurv")

• Check out the main fitter function examples.

library("KMsurv")data("larynx")library(spsurv)## Maximum Likelihoodfit<-spbp(Surv(time, delta)~age+factor(stage),approach ="mle",data = larynx)summary(fit)## NUTS sampling (Bayesian)fit2<-spbp(Surv(time, delta)~age+factor(stage),approach ="bayes",data = larynx,iter =2000,chains =1,warmup =1000)summary(fit2)

Thespsurv already provides: - Integration with Stansoftware. - Estimates either in Bayesian or Frequentist (point estimate)inferential approaches. - Three survival regression classes: PH, PO andAFT. - Six distinct prior specifications in a Bayesian analysis.