Fast randomization based two sample tests. Testing the hypothesis that two samples come from the same distribution using randomization to create p-values. Included tests are: Kolmogorov-Smirnov, Kuiper, Cramer-von Mises, Anderson-Darling, Wasserstein, and DTS. The default test (two_sample) is based on the DTS test statistic, as it is the most powerful, and thus most useful to most users. The DTS test statistic builds on the Wasserstein distance by using a weighting scheme like that of Anderson-Darling. See the companion paper at <arXiv:2007.01360> or <https://codowd.com/public/DTS.pdf> for details of that test statistic, and non-standard uses of the package (parallel for big N, weighted observations, one sample tests, etc). We also include the permutation scheme to make test building simple for others.
Version: | 1.1.1 |
Imports: | Rcpp (≥ 0.12.17) |
LinkingTo: | Rcpp |
Published: | 2020-07-19 |
Author: | Connor Dowd |
Maintainer: | Connor Dowd <cdowd at chicagobooth.edu> |
BugReports: | https://github.com/cdowd/twosamples/issues |
License: | GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |
URL: | https://github.com/cdowd/twosamples |
NeedsCompilation: | yes |
Materials: | README NEWS |
CRAN checks: | twosamples results |
Reference manual: | twosamples.pdf |
Package source: | twosamples_1.1.1.tar.gz |
Windows binaries: | r-devel: twosamples_1.1.1.zip, r-release: twosamples_1.1.1.zip, r-oldrel: twosamples_1.1.1.zip |
macOS binaries: | r-release: twosamples_1.1.1.tgz, r-oldrel: twosamples_1.1.1.tgz |
Old sources: | twosamples archive |
Please use the canonical form https://CRAN.R-project.org/package=twosamples to link to this page.