Multiple Imputation for Recurrent Events

Performs reference based multiple imputation of recurrent event data based on a negative binomial regression model, as described by Keene et al (2014) .

Build Status CRAN_Status_Badge Coverage Status Build status CRAN RStudio mirror downloads CRAN RStudio mirror downloads

Multiple Imputation for Recurent Event Endpoints in Clinical Trials

The dejaVu package performs multiple imputation on recurrent event data sets, following the approach described by Keene et al. The package can be used to perform multiple imputation of an existing study dataset where some patients dropped out. Imputation can be performed either assuming dropout is at random (missing at random) or assuming a specific non-random dropout mechanism (missing not at random). The package can also be used to simulate recurrent event datasets, in order to evaluate the impact of dropout and the properties of multiple imputation based analyses. Finally, the imputed data sets can be analysed and their results combined using Rubin’s rules.


Bartlett, Jonathan (maintainer); Burkoff, Nikolas; Metcalfe, Paul; Ruau, David;


To install the development version from GitHub:

# We spent a lot of time developing the vignettes. We recommend the read but 
# building them from source takes some time
                         build_vignettes = TRUE)


Version 0.2.0 - first release on CRAN

Reference manual

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


0.2.0 by Jonathan Bartlett, 2 years ago

Browse source code at

Authors: c(person("Nikolas" , "Burkoff" , role=c("aut")) , person("Paul" , "Metcalfe" , email='[email protected]' , role=c("aut")) , person("Jonathan" , "Bartlett" , email='[email protected]' , role=c("aut")) , person("David" , "Ruau" , email='[email protected]' , role=c("aut")) )

Documentation:   PDF Manual  

Task views: Missing Data

GPL (>= 2) license

Imports MASS, stats

Suggests knitr, testthat

See at CRAN