Statistics, Department of

The R Journal
Date of this Version
8-2016
Document Type
Article
Citation
The R Journal (August 2016) 8(1); Editor: Michael Lawrence
Abstract
n this article, we introduce the R package CryptRndTest that performs eight statistical randomness tests on cryptographic random number sequences. The purpose of the package is to provide software implementing recently proposed cryptographic randomness tests utilizing goodness of-fit tests superior to the usual chi-square test in terms of statistical performance. Most of the tests included in package CryptRndTest are not available in other software packages such as the R package RDieHarder or the C library TestU01. Chi-square, Anderson-Darling, Kolmogorov-Smirnov, and Jarque-Bera goodness-of-fit procedures are provided along with cryptographic randomness tests. CryptRndTest utilizes multiple precision floating numbers for sequences longer than 64-bit based on the package Rmpfr. By this way, included tests are applied precisely for higher bit-lengths. In addition CryptRndTest provides a user friendly interface to these cryptographic randomness tests. As an illustrative application, CryptRndTest is used to test available random number generators in R.
Included in
Numerical Analysis and Scientific Computing Commons, Programming Languages and Compilers Commons
Comments
Copyright 2016, The R Foundation. Open access material. License: CC BY 3.0 Unported