Computing the Oja Median in R: The Package OjaNP

Daniel Fischer, Karl Mosler, Jyrki Möttönen, Klaus Nordhausen, Oleksii Pokotylo, Daniel Vogel

Research output: Working paper

Abstract

The Oja median is one of several extensions of the univariate median to the multivariate case. It has many nice properties, but is computationally demanding. In this paper, we first review the properties of the Oja median and compare it to other multivariate medians. Afterwards we discuss four algorithms to compute the Oja median, which are implemented in our R-package OjaNP. Besides these algorithms, the package contains also functions to compute Oja signs, Oja signed ranks, Oja ranks, and the related scatter concepts. To illustrate their use, the corresponding multivariate one- and $C$-sample location tests are implemented.
Original languageEnglish
PublisherArXiv
Pages1-36
Number of pages36
Publication statusSubmitted - 24 Jun 2016

Keywords

  • Oja median
  • Oja signs
  • Oja signed ranks
  • Oja ranks
  • R,C,C++

Cite this

Fischer, D., Mosler, K., Möttönen, J., Nordhausen, K., Pokotylo, O., & Vogel, D. (2016). Computing the Oja Median in R: The Package OjaNP. (pp. 1-36). ArXiv.

Computing the Oja Median in R : The Package OjaNP. / Fischer, Daniel; Mosler, Karl; Möttönen, Jyrki; Nordhausen, Klaus; Pokotylo, Oleksii; Vogel, Daniel.

ArXiv, 2016. p. 1-36.

Research output: Working paper

Fischer, D, Mosler, K, Möttönen, J, Nordhausen, K, Pokotylo, O & Vogel, D 2016 'Computing the Oja Median in R: The Package OjaNP' ArXiv, pp. 1-36.
Fischer D, Mosler K, Möttönen J, Nordhausen K, Pokotylo O, Vogel D. Computing the Oja Median in R: The Package OjaNP. ArXiv. 2016 Jun 24, p. 1-36.
Fischer, Daniel ; Mosler, Karl ; Möttönen, Jyrki ; Nordhausen, Klaus ; Pokotylo, Oleksii ; Vogel, Daniel. / Computing the Oja Median in R : The Package OjaNP. ArXiv, 2016. pp. 1-36
@techreport{a0702bcb2f34404cb6704947d3ff98c1,
title = "Computing the Oja Median in R: The Package OjaNP",
abstract = "The Oja median is one of several extensions of the univariate median to the multivariate case. It has many nice properties, but is computationally demanding. In this paper, we first review the properties of the Oja median and compare it to other multivariate medians. Afterwards we discuss four algorithms to compute the Oja median, which are implemented in our R-package OjaNP. Besides these algorithms, the package contains also functions to compute Oja signs, Oja signed ranks, Oja ranks, and the related scatter concepts. To illustrate their use, the corresponding multivariate one- and $C$-sample location tests are implemented.",
keywords = "Oja median, Oja signs, Oja signed ranks, Oja ranks, R,C,C++",
author = "Daniel Fischer and Karl Mosler and Jyrki M{\"o}tt{\"o}nen and Klaus Nordhausen and Oleksii Pokotylo and Daniel Vogel",
note = "Acknowledgements The work of Klaus Nordhausen was supported by the Academy of Finland (grant 268703). Oleksii Pokotylo is supported by the Cologne Graduate School of Management, Economics and Social Sciences. The work of Daniel Vogel was supported by the DFG collaborate research grant SFB 823",
year = "2016",
month = "6",
day = "24",
language = "English",
pages = "1--36",
publisher = "ArXiv",
type = "WorkingPaper",
institution = "ArXiv",

}

TY - UNPB

T1 - Computing the Oja Median in R

T2 - The Package OjaNP

AU - Fischer, Daniel

AU - Mosler, Karl

AU - Möttönen, Jyrki

AU - Nordhausen, Klaus

AU - Pokotylo, Oleksii

AU - Vogel, Daniel

N1 - Acknowledgements The work of Klaus Nordhausen was supported by the Academy of Finland (grant 268703). Oleksii Pokotylo is supported by the Cologne Graduate School of Management, Economics and Social Sciences. The work of Daniel Vogel was supported by the DFG collaborate research grant SFB 823

PY - 2016/6/24

Y1 - 2016/6/24

N2 - The Oja median is one of several extensions of the univariate median to the multivariate case. It has many nice properties, but is computationally demanding. In this paper, we first review the properties of the Oja median and compare it to other multivariate medians. Afterwards we discuss four algorithms to compute the Oja median, which are implemented in our R-package OjaNP. Besides these algorithms, the package contains also functions to compute Oja signs, Oja signed ranks, Oja ranks, and the related scatter concepts. To illustrate their use, the corresponding multivariate one- and $C$-sample location tests are implemented.

AB - The Oja median is one of several extensions of the univariate median to the multivariate case. It has many nice properties, but is computationally demanding. In this paper, we first review the properties of the Oja median and compare it to other multivariate medians. Afterwards we discuss four algorithms to compute the Oja median, which are implemented in our R-package OjaNP. Besides these algorithms, the package contains also functions to compute Oja signs, Oja signed ranks, Oja ranks, and the related scatter concepts. To illustrate their use, the corresponding multivariate one- and $C$-sample location tests are implemented.

KW - Oja median

KW - Oja signs

KW - Oja signed ranks

KW - Oja ranks

KW - R,C,C++

M3 - Working paper

SP - 1

EP - 36

BT - Computing the Oja Median in R

PB - ArXiv

ER -