README.md

In sa4khan/AFTjmr: Recurrent event analysis and joint modeling using accelerated failure time (AFT) models

AFTjmr: Accelerated Failure Time Models for Recurrent Event Data Analysis and Joint Modeling

An R package for recurrent event data analysis and joint modeling using accelerated failure time (AFT) models. It also includes fitting AFT models for right censored (non-recurrent) time-to-event data. Available models are Weibull, log-logistic, log-normal, exponentiated Weibull and generalized gamma. Maximum likelihood method is used to fit recurrent event models, and Bayesian approach (implemented in JAGS) is used for joint modeling. The package dclone is used for parallel computation in JAGS for MCMC. Note that JAGS must be installed for MCMC. See the pdf manual for details.

Inatallation:

Step 1: Install JAGS (http://mcmc-jags.sourceforge.net/)

Step 2: From R,

library(devtools)

install_github("sa4khan/AFTjmr")

Main functions for Recurrent Event Data Analysis

survreg.aft: Fit a parametric AFT model to time-to-event data

surv.resid: Cox-Snell residuals of survreg.aft fits

LR.test: Likelihood ratio test for Weibull as a submodel of the exponentiated Weibull or generalized gamma model

sim.rec: Simulate recurrent event data for fixed covariates

Main functions for Joint Modeling

jmreg.aft: Fit a joint model

jm.summary: Summary of a joint model fit

jm.resid.plot: Cox-Snell residual plot for the event process of the joint model

jm.reffects: Posterior means/medians of the random effects from a joint model fit

jm.DIC: Computes DIC for Bayesian fit of the joint model

jm.WAIC: Computes WAIC for Bayesian fit of the joint model

jm.surv: Dynamic predictions of survival probabilites

jm.sim: Simulate from joint models

sa4khan/AFTjmr documentation built on March 12, 2020, 1:24 a.m.