blockRAR: Block Design for Response Adaptive Randomization

Authors: Thevaa Chandereng and Rick Chappell

Overview

Response-Adaptive Randomization (RAR) is an adaptive trial where the randomization ratio of the patient changes based on the patient's performance and treatment assignment. However, most designs completely ignores the time trend aspect in this design and the randomization ratio's are altered based on patient's outcomes. blockRAR assigns patient in a block (group) manner and the the block results are analyzed before the randomization ratio is altered. Time is divided into factor level in each block (group). The treatment effect is obtained upon adjusting for the time effect in this design. The blockRAR website is available here.

Installation

Prior to analyzing your data, the R package needs to be installed.

The easiest way to install blockRAR is through CRAN:

install.packages("blockRAR")

There are other additional ways to download blockRAR. The first option is most useful if want to download a specific version of blockRAR (which can be found at https://github.com/thevaachandereng/blockRAR/releases).

devtools::install_github("thevaachandereng/blockRAR@vx.xx.x")
# OR 
devtools::install_version("blockRAR", version = "x.x.x", repos = "http://cran.us.r-project.org")

The second option is to download through GitHub.

devtools::install_github("thevaachandereng/blockRAR")

After successful installation, the package must be loaded into the working space:

library(blockRAR)

Usage

See the vignette for usage instructions.

Reference

If you use blockRAR, please cite:

Chandereng, T., & Chappell, R. (2019). Robust Response-Adaptive Randomization Design. arXiv preprint arXiv:1904.07758.

License

blockRAR is available under the open source MIT license.