The R Journal: accepted article

This article will be copy edited and may be changed before publication.

miRecSurv Package: Prentice-Williams-Peterson Models with Multiple Imputation of Unknown Number of Previous Episodes PDF download
David Moriña, Gilma Hernández-Herrera and Albert Navarro

Abstract Left censoring can occur with relative frequency when analysing recurrent events in epi demiological studies, especially observational ones. Concretely, the inclusion of individuals that were already at risk before the effective initiation in a cohort study, may cause the unawareness of prior episodes that have already been experienced, and this will easily lead to biased and inefficient estimates. The miRecSurv package is based on the use of models with specific baseline hazard, with multiple imputation of the number of prior episodes when unknown by means of the COMPoisson distribution, a very flexible count distribution that can handle over-, suband equidispersion, with a stratified model depending on whether the individual had or had not previously been at risk, and the use of a frailty term. The usage of the package is illustrated by means of a real data example based on a occupational cohort study and a simulation study.

Received: ; online 2021-09-20, supplementary material, (2.9 Kb)
CRAN packages: miRecSurv, compoisson, survsim
CRAN Task Views implied by cited CRAN packages: Survival


CC BY 4.0
This article and supplementary materials are licensed under a Creative Commons Attribution 4.0 International license.

@article{RJ-2021-082,
  author = {David Moriña and Gilma Hernández-Herrera and Albert Navarro},
  title = {{miRecSurv Package: Prentice-Williams-Peterson Models with
          Multiple Imputation of Unknown Number of Previous
          Episodes}},
  year = {2021},
  journal = {{The R Journal}},
  doi = {10.32614/RJ-2021-082},
  url = {https://journal.r-project.org/archive/2021/RJ-2021-082/index.html}
}