MSPRT: A Modified Sequential Probability Ratio Test (MSPRT)

A modified SPRT (MSPRT) can be designed and implemented with the help of this package. In a MSPRT design, (i) the maximum sample size of an experiment is fixed prior to the start of an experiment; (ii) the alternative hypothesis used to define the rejection region of the test is derived from the size of the test (Type I error), the maximum available sample size (N), and (iii) the targeted Type 2 error (equals to 1 minus the power) is also prespecified. Given these values, the MSPRT is defined in a manner very similar to Wald's initial proposal. This test can reduce the average sample size required to perform statistical hypothesis tests at the specified level of significance and power. This package implements one-sample proportion tests, one-sample Z-tests, one-sample T-tests, two-sample Z-tests and two-sample T-tests. A user guidance for this package is provided here. One can also refer to the supplemental information for the same.

Version: 2.1
Imports: nleqslv, ggplot2, foreach, iterators, parallel, doParallel, datasets, graphics, grDevices, methods, stats, utils
Published: 2019-08-19
Author: Sandipan Pramanik [aut, cre], Valen E. Johnson [aut], Anirban Bhattacharya [aut]
Maintainer: Sandipan Pramanik <sandy at stat.tamu.edu>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
CRAN checks: MSPRT results

Downloads:

Reference manual: MSPRT.pdf
Package source: MSPRT_2.1.tar.gz
Windows binaries: r-devel: MSPRT_2.1.zip, r-devel-gcc8: MSPRT_2.1.zip, r-release: MSPRT_2.1.zip, r-oldrel: MSPRT_2.1.zip
OS X binaries: r-release: MSPRT_2.1.tgz, r-oldrel: MSPRT_2.1.tgz
Old sources: MSPRT archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=MSPRT to link to this page.