Group Sequential Design with Non-Constant Effect R package gsDesign2 version 1.2.0 The goal of 'gsDesign2' is to enable fixed or group sequential design under non-proportional hazards. To enable highly flexible enrollment, time-to-event and time-to-dropout assumptions, 'gsDesign2' offers piecewise constant enrollment, failure rates, and dropout rates for a stratified population. This package includes three methods for designs: average hazard ratio, weighted logrank tests in Yung and Liu (2019) <doi:10.1111/biom.13196>, and MaxCombo tests. Substantial flexibility on top of what is in the 'gsDesign' package is intended for selecting boundaries. Software Depends: R (>= 4.1.0) Imports: corpcor, data.table, dplyr, gsDesign, gt, methods, mvtnorm, npsurvSS (>= 1.1.0), r2rtf, stats, survival, tibble, tidyr, utils, Rcpp LinkingTo: Rcpp Suggests: covr, ggplot2, cowplot, kableExtra, knitr, rmarkdown, simtrial, testit (>= 1.0) Yujie Zhao <yujie.zhao@merck.com> Comprehensive R Archive Network (CRAN) Keaven Anderson [aut], Yujie Zhao [aut, cre], Yilong Zhang [aut], John Blischak [aut], Yihui Xie [aut], Nan Xiao [aut], Jianxiao Yang [aut], Amin Shirazi [ctb], Ruixue Wang [ctb], Yi Cui [ctb], Ping Yang [ctb], Xin Tong Li [ctb], Chenxiang Li [ctb], Hiroaki Fukuda [ctb], Hongtao Zhang [ctb], Yalin Zhu [ctb], Shiyu Zhang [ctb], Dickson Wanjau [ctb], Merck & Co., Inc., Rahway, NJ, USA and its affiliates [cph] (ROR: <https://ror.org/02891sr49>) GPL-3 2026-07-30 application/tgz https://CRAN.R-project.org/package=gsDesign2 doi:10.32614/CRAN.package.gsDesign2