gset: An R Package for Exact Sequential Test of Equivalence Hypothesis Based on Bivariate Non-Central t-Statistics

Authors

• Fang Liu, The University of Notre Dame

Date of this Version

12-2014

Document Type

Article

Citation

The R Journal (December 2014) 6(2); Editor: Deepayan Sarkar

Comments

Copyright 2014, The R Foundation. Open access material. License: CC BY 3.0 Unported

Abstract

The R package gset calculates equivalence and futility boundaries based on the exact bivariate non-central t test statistics. It is the first R package that targets specifically at the group sequential test of equivalence hypotheses. The exact test approach adopted by gset neither assumes the large-sample normality of the test statistics nor ignores the contribution to the overall Type I error rate from rejecting one out of the two one-sided hypotheses under a null value. The features of gset include: error spending functions, computation of equivalence boundaries and futility boundaries, either binding or nonbinding, depiction of stagewise boundary plots, and operating characteristics of a given group sequential design including empirical Type I error rate, empirical power, expected sample size, and probability of stopping at an interim look due to equivalence or futility.