Published by the Foundation for Open Access Statistics Editors-in-chief: Bettina Grün, Torsten Hothorn, Rebecca Killick, Edzer Pebesma, Achim Zeileis    ISSN 1548-7660; CODEN JSSOBK
[test by reto]
Authors: James Wason
Title: OptGS: An R Package for Finding Near-Optimal Group-Sequential Designs
Abstract: A group-sequential clinical trial design is one in which interim analyses of the data are conducted after groups of patients are recruited. After each interim analysis, the trial may stop early if the evidence so far shows the new treatment is particularly effective or ineffective. Such designs are ethical and cost-effective, and so are of great interest in practice. An optimal group-sequential design is one which controls the type-I error rate and power at a specified level, but minimizes the expected sample size of the trial when the true treatment effect is equal to some specified value. Searching for an optimal groupsequential design is a significant computational challenge because of the high number of parameters. In this paper the R package OptGS is described. Package OptGS searches for near-optimal and balanced (i.e., one which balances more than one optimality criterion) group-sequential designs for randomized controlled trials with normally distributed outcomes. Package OptGS uses a two-parameter family of functions to determine the stopping boundaries, which improves the speed of the search process whilst still allowing flexibility in the possible shape of stopping boundaries. The resulting package allows optimal designs to be found in a matter of seconds – much faster than a previous approach.

Page views:: 1761. Submitted: 2012-02-14. Published: 2015-08-26.
Paper: OptGS: An R Package for Finding Near-Optimal Group-Sequential Designs     Download PDF (Downloads: 2348)
OptGS_1.1.1.tar.gz: R source package Download (Downloads: 104; 12KB)
v66i02.R: R example code from the paper Download (Downloads: 145; 3KB) Supplementary C++ replication code Download (Downloads: 61; 7KB)

DOI: 10.18637/jss.v066.i02

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.