Networks: On the relation of bi- and multivariate measures

Wolfgang Mader, Malenka Mader, Jens Timmer, Marco Thiel, Bjoern Schelter

Research output: Contribution to journalArticle

8 Citations (Scopus)
7 Downloads (Pure)

Abstract

A reliable inference of networks from observations of the nodes’ dynamics is a major challenge in physics. Interdependence measures such as a the correlation coefficient or more advanced methods based on, e.g., analytic phases of signals are employed. For several of these interdependence measures, multivariate counterparts exist that promise to enable distinguishing direct and indirect connections. Here, we demonstrate analytically how bivariate measures relate to the respective multivariate ones; this knowledge will in turn be used to demonstrate the implications of thresholded bivariate measures for network inference. Particularly, we show, that random networks are falsely identified as small-world networks if observations thereof are treated by bivariate methods. We will employ the correlation coefficient as an example for such an interdependence measure. The results can be readily transferred to all interdependence measures partializing for information of thirds in their multivariate counterparts.
Original languageEnglish
Article number10805
Number of pages7
JournalScientific Reports
Volume5
Early online date4 Jun 2015
DOIs
Publication statusPublished - 4 Jun 2015

Fingerprint

inference
correlation coefficients
physics

Cite this

Networks : On the relation of bi- and multivariate measures. / Mader, Wolfgang; Mader, Malenka; Timmer, Jens; Thiel, Marco; Schelter, Bjoern.

In: Scientific Reports, Vol. 5, 10805, 04.06.2015.

Research output: Contribution to journalArticle

@article{6df240a177154a0db20a0be33e8fc499,
title = "Networks: On the relation of bi- and multivariate measures",
abstract = "A reliable inference of networks from observations of the nodes’ dynamics is a major challenge in physics. Interdependence measures such as a the correlation coefficient or more advanced methods based on, e.g., analytic phases of signals are employed. For several of these interdependence measures, multivariate counterparts exist that promise to enable distinguishing direct and indirect connections. Here, we demonstrate analytically how bivariate measures relate to the respective multivariate ones; this knowledge will in turn be used to demonstrate the implications of thresholded bivariate measures for network inference. Particularly, we show, that random networks are falsely identified as small-world networks if observations thereof are treated by bivariate methods. We will employ the correlation coefficient as an example for such an interdependence measure. The results can be readily transferred to all interdependence measures partializing for information of thirds in their multivariate counterparts.",
author = "Wolfgang Mader and Malenka Mader and Jens Timmer and Marco Thiel and Bjoern Schelter",
note = "Date of Acceptance: 28/04/2015 Acknowledgement The article processing charge was funded by the German Research Foundation (DFG) and the Albert Ludwigs University Freiburg in the funding programme Open Access Publishing",
year = "2015",
month = "6",
day = "4",
doi = "10.1038/srep10805",
language = "English",
volume = "5",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Networks

T2 - On the relation of bi- and multivariate measures

AU - Mader, Wolfgang

AU - Mader, Malenka

AU - Timmer, Jens

AU - Thiel, Marco

AU - Schelter, Bjoern

N1 - Date of Acceptance: 28/04/2015 Acknowledgement The article processing charge was funded by the German Research Foundation (DFG) and the Albert Ludwigs University Freiburg in the funding programme Open Access Publishing

PY - 2015/6/4

Y1 - 2015/6/4

N2 - A reliable inference of networks from observations of the nodes’ dynamics is a major challenge in physics. Interdependence measures such as a the correlation coefficient or more advanced methods based on, e.g., analytic phases of signals are employed. For several of these interdependence measures, multivariate counterparts exist that promise to enable distinguishing direct and indirect connections. Here, we demonstrate analytically how bivariate measures relate to the respective multivariate ones; this knowledge will in turn be used to demonstrate the implications of thresholded bivariate measures for network inference. Particularly, we show, that random networks are falsely identified as small-world networks if observations thereof are treated by bivariate methods. We will employ the correlation coefficient as an example for such an interdependence measure. The results can be readily transferred to all interdependence measures partializing for information of thirds in their multivariate counterparts.

AB - A reliable inference of networks from observations of the nodes’ dynamics is a major challenge in physics. Interdependence measures such as a the correlation coefficient or more advanced methods based on, e.g., analytic phases of signals are employed. For several of these interdependence measures, multivariate counterparts exist that promise to enable distinguishing direct and indirect connections. Here, we demonstrate analytically how bivariate measures relate to the respective multivariate ones; this knowledge will in turn be used to demonstrate the implications of thresholded bivariate measures for network inference. Particularly, we show, that random networks are falsely identified as small-world networks if observations thereof are treated by bivariate methods. We will employ the correlation coefficient as an example for such an interdependence measure. The results can be readily transferred to all interdependence measures partializing for information of thirds in their multivariate counterparts.

U2 - 10.1038/srep10805

DO - 10.1038/srep10805

M3 - Article

VL - 5

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 10805

ER -