Published by the Foundation for Open Access Statistics
Editors-in-chief: Bettina Grün, Torsten Hothorn, Edzer Pebesma, Achim Zeileis    ISSN 1548-7660; CODEN JSSOBK
Dynamic Treatment Regimen Estimation via Regression-Based Techniques: Introducing R Package DTRreg | Wallace | Journal of Statistical Software
Authors: Michael P. Wallace, Erica E. M. Moodie, David A. Stephens
Title: Dynamic Treatment Regimen Estimation via Regression-Based Techniques: Introducing R Package DTRreg
Abstract: Personalized medicine, whereby treatments are tailored to a specific patient rather than a general disease or condition, is an area of growing interest in the fields of biostatistics, epidemiology, and beyond. Dynamic treatment regimens (DTRs) are an integral part of this framework, allowing for personalized treatment of patients with long-term conditions while accounting for both their present circumstances and medical history. The identification of the optimal DTR in any given context, however, is a non-trivial problem, and so specialized methodologies have been developed for that purpose. Here we introduce the R package DTRreg which implements two regression-based approaches: G-estimation and dynamic weighted ordinary least squares regression. We outline the theory underlying these methods, discuss the implementation of DTRreg and demonstrate its use with hypothetical and real-world inspired simulated datasets.

Page views:: 1437. Submitted: 2015-06-09. Published: 2017-08-31.
Paper: Dynamic Treatment Regimen Estimation via Regression-Based Techniques: Introducing R Package DTRreg     Download PDF (Downloads: 575)
Supplements:
DTRreg_1.3.tar.gz: R source package Download (Downloads: 43; 15KB)
v80i02.R: R replication code Download (Downloads: 57; 8KB)
Simulated_PROBIT_data.csv: Supplementary data (CSV format) Download (Downloads: 46; 1MB)

DOI: 10.18637/jss.v080.i02

by
This work is licensed under the licenses
Paper: Creative Commons Attribution 3.0 Unported License
Code: GNU General Public License (at least one of version 2 or version 3) or a GPL-compatible license.