wnpmle: Weighted NPMLE for Recurrent Events with a Competing Terminal Event

Provides regression modeling and prediction for the marginal mean of recurrent events in the presence of a competing terminal event using the weighted nonparametric maximum likelihood estimator (wNPMLE) of Bellach and Kosorok (2026) <doi:10.48550/arXiv.2605.25934>. Two classes of transformation models are implemented: Box-Cox transformation models and logarithmic transformation models. These extend the proportional means model of Ghosh and Lin (2002) <doi:10.17615/pt0g-y207> and the transformation model framework of Zeng and Lin (2006) <doi:10.1093/biomet/93.3.627>. Parameter estimation is performed using automatic differentiation through the Template Model Builder (TMB) framework. Standard errors are computed using sandwich variance estimators that account for estimation of the inverse-probability censoring weights following Bellach, Kosorok, Rüschendorf and Fine (2019) <doi:10.1080/01621459.2017.1401540>.

Version:	0.1.2
Depends:	R (≥ 4.1.0)
Imports:	TMB (≥ 1.9.0), survival, methods, MASS, graphics, grDevices
Suggests:	testthat (≥ 3.0.0), knitr, rmarkdown
Published:	2026-06-18
DOI:	10.32614/CRAN.package.wnpmle
Author:	Anna Bellach [aut, cre]
Maintainer:	Anna Bellach <abellach.biostat at gmail.com>
BugReports:	https://github.com/abellach/wnpmle/issues
License:	GPL (≥ 3)
URL:	https://github.com/abellach/wnpmle
NeedsCompilation:	no
Materials:	README
CRAN checks:	wnpmle results

Documentation:

Reference manual:	wnpmle.html , wnpmle.pdf
Vignettes:	Getting Started with wnpmle (source, R code)

Downloads:

Package source:	wnpmle_0.1.2.tar.gz
Windows binaries:	r-devel: wnpmle_0.1.2.zip, r-release: wnpmle_0.1.2.zip, r-oldrel: wnpmle_0.1.2.zip
macOS binaries:	r-release (arm64): wnpmle_0.1.2.tgz, r-oldrel (arm64): wnpmle_0.1.2.tgz, r-release (x86_64): wnpmle_0.1.2.tgz, r-oldrel (x86_64): wnpmle_0.1.2.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=wnpmle to link to this page.