Abstract
We introduce an R package PGEE that implements the penalized generalized estimating equations (GEE) procedure proposed byWang et al. (2012) to analyze longitudinal data with a large number of covariates. The PGEE package includes three main functions: CVfit, PGEE, and MGEE. The CVfit function computes the cross-validated tuning parameter for penalized generalized estimating equations. The function PGEE performs simultaneous estimation and variable selection for longitudinal data with high-dimensional covariates; whereas the function MGEE fits unpenalized GEE to the data for comparison. The R package PGEE is illustrated using a yeast cell-cycle gene expression data set.
Original language | English |
---|---|
Pages (from-to) | 393-402 |
Number of pages | 10 |
Journal | R Journal |
Volume | 9 |
Issue number | 1 |
DOIs | |
Publication status | Published - 1 Jun 2017 |
Externally published | Yes |