RetroSearch Browse

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/jrdnmdhl/flexsurvcure below:

jrdnmdhl/flexsurvcure: Parametric cure models for flexsurvreg

The development repository for flexsurvcure, an R package for parametric mixture and non-mixture cure models. Flexsurvcure is based on flexsurv, the R package for parametric survival modelling.

Installation (development version)

install.packages("flexsurv")
install.packages("devtools")
devtools::install_github('jrdnmdhl/flexsurvcure')

All of the built-in distribution with flexsurvreg are supported, though some currently have issues with convergence and numerical instability. The following distributions currently seem reliable:

Exponential (exp)
Weibull (weibull, weibullPH)
Lognormal (lnorm)
Log-Logistic (llogis)

The following distributions are supported, but may not be reliable:

Gompertz (gompertz)
Generalized Gamma (gengamma, gengamma.orig)
Generalized F (genf, genf.orig)

Custom distributions can also be used by passing a distribution list (see flexsurv examples).

Fitting a mixture cure model

mixture = flexsurvcure(Surv(rectime,censrec)~group, data=bc, dist="weibullPH", link="logistic", mixture = T)
plot(mixture)

Fitting a non-mixture cure model

non_mixture = flexsurvcure(Surv(rectime,censrec)~group, data=bc, dist="weibullPH", link="loglog", mixture = F)
plot(non_mixture)

Covariates on parameters other than cure fraction

non_mixture_covarite_scale = flexsurvcure(Surv(rectime,censrec)~group, data=bc, anc=list(scale=~group), dist="weibullPH", link="loglog", mixture = F)
plot(non_mixture_covarite_scale)

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4