HRM: An R package for analysing high-dimensional multi-factor repeated measures

Martin Happ, Solomon W. Harrar, Arne C. Bathke

Research output: Contribution to journalArticlepeer-review

Abstract

High-dimensional longitudinal data pose a serious challenge for statistical inference as many test statistics cannot be computed for high-dimensional data, or they do not maintain the nominal type-I error rate, or have very low power. Therefore, it is necessary to derive new inference methods capable of dealing with high dimensionality, and to make them available to statistics practitioners. One such method is implemented in the package HRM described in this article. This new method uses a similar approach as the Welch-Satterthwaite t-test approximation and works very well for high-dimensional data as long as the data distribution is not too skewed or heavy-tailed. The package also provides a GUI to offer an easy way to apply the methods.

Original languageEnglish
Pages (from-to)534-548
Number of pages15
JournalR Journal
Volume10
Issue number1
DOIs
StatePublished - Jul 1 2018

Bibliographical note

Publisher Copyright:
© The R Foundation.

ASJC Scopus subject areas

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Fingerprint

Dive into the research topics of 'HRM: An R package for analysing high-dimensional multi-factor repeated measures'. Together they form a unique fingerprint.

Cite this