The R Journal: accepted article

This article will be copy edited and may be changed before publication.

Nonparametric independence tests and K-sample tests for large sample sizes, using package HHG PDF download
Barak Brill, Yair Heller and Ruth Heller

Abstract Nonparametric tests of independence and K-sample tests are ubiquitous in modern applica tions, but they are typically computationally expensive. We present a family of nonparametric tests that are computationally efficient and powerful for detecting any type of dependence between a pair of univariate random variables. The computational complexity of the suggested tests is sub-quadratic in sample size, allowing calculation of test statistics for millions of observations. We survey both algorithms and the HHG package in which they are implemented, with usage examples showing the implementation of the proposed tests for both the independence case and the K-sample problem. The tests are compared to existing nonparametric tests via several simulation studies comparing both runtime and power. Special focus is given to the design of data structures used in implementation of the tests. These data structures can be useful for developers of nonparametric distribution-free tests.

Received: 2017-10-23; online 2018-05-16, supplementary material, (20.8 Kb)
CRAN packages: Hmisc, infotheo, entropy, minerva, dHSIC, energy, HHG, kernlab, dslice, rbenchmark, doRNG
CRAN Task Views implied by cited CRAN packages: Multivariate, Bayesian, ClinicalTrials, Cluster, Econometrics, HighPerformanceComputing, MachineLearning, NaturalLanguageProcessing, OfficialStatistics, Optimization, ReproducibleResearch, SocialSciences
Bioconductor packages: minet


CC BY 4.0
This article and supplementary materials are licensed under a Creative Commons Attribution 4.0 International license.

@article{RJ-2018-008,
  author = {Barak Brill and Yair Heller and Ruth Heller},
  title = {{Nonparametric independence tests and K-sample tests for
          large sample sizes, using package HHG}},
  year = {2018},
  journal = {{The R Journal}},
  url = {https://journal.r-project.org/archive/2018/RJ-2018-008/index.html}
}