pgf is an R implementation of the parametric g formula, first developed by Robins in the mid 1980s. The purpose of this program is to simulate the follow-up of a cohort study with complex longitudinal data under different exposure regimes. pgf accomplishes this in two steps:
-
Fit empirical models to the observed complex longitudinal dataset.
-
Simulate follow-up from each model, but setting the exposure/censoring values to desired levels.
You can install the latest development version from github with
```R
install.packages("devtools")
devtools::install_github("ainaimi/pgf")
```
If you encounter a bug or other issue, please file a request on github.
A vignette for the pgf package is currently in preparation. To learn about the parametric g formula more generally, please refer to the following citations: