Restricted Mean Time in Favor of Treatment

Estimates restricted mean time in favor of treatment from ordered multistate trajectories, with lower states denoting better outcomes. Provides complete-path pairwise estimation, projection standard errors, normal confidence intervals and tests, terminal-aware inverse probability of censoring weighting, stratified bootstrap inference, and pairwise regression with sandwich or refitted-bootstrap inference. Includes parameterized simulation and Monte Carlo summary tools for reversible processes, continuous-time Markov paths, constant-utility regression, and comparisons of longitudinal oncology endpoints. The restricted-time estimand follows Mao (2023) ; pairwise regression is motivated by the proportional win-fractions framework of Mao and Wang (2021) .


RMTIF

Estimate restricted mean time in favor of treatment from ordered state paths. Lower numeric states denote better outcomes. Estimation is available for complete paths and paths subject to independent censoring; inference includes projection standard errors, normal intervals, two-sided tests, and stratified bootstrap methods that re-estimate the censoring distribution.

Install the source archive with base R:

install.packages("RMTIF_0.3.1.tar.gz", repos = NULL, type = "source")
library(RMTIF)

For example, obtain projection inference from a matrix of pairwise net times whose rows identify control subjects and columns identify treatment subjects:

net <- matrix(c(1, 2, 3, 4), nrow = 2, byrow = TRUE)
rmtif_projection_inference(net, conf_level = 0.95)

The R source is copied byte for byte from the accompanying functions_v1.2.R. The separate examples_v1.2.R contains manuscript design settings and writes the manuscript tables. Long manuscript Monte Carlo runs are excluded from package examples and tests. Function help includes concise examples using independently chosen illustration inputs.

Method references

The restricted-time estimand follows Mao (2023), "On restricted mean time in favor of treatment", Biometrics 79, 61-72, doi:10.1111/biom.13570. The pairwise regression is motivated by Mao and Wang (2021), "A class of proportional win-fractions regression models for composite outcomes", Biometrics 77, 1265-1275, doi:10.1111/biom.13382.

The manuscript describing this package's reversible-path extensions is unpublished and currently has no public URL or DOI. The references above identify the published foundations; package help documents the implemented estimators and functions.

Study functions return summary, replicate, design, and runtime data frames. They run quietly in both serial and parallel execution. Users can explicitly print or save the returned information they need.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("RMTIF")

0.3.1 by Mohsen Rezapour, 16 hours ago


Browse source code at https://github.com/cran/RMTIF


Authors: Mohsen Rezapour [aut, cre]


Documentation:   PDF Manual  


GPL (>= 3) license


Imports stats, utils, parallel

Suggests MASS, survival, Wcompo


See at CRAN