Influence of measurement errors on networks: Estimating the robustness of centrality measures

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Influence of measurement errors on networks: Estimating the robustness of centrality measures. / Martin, Christoph; Niemeyer, Peter.
In: Network Science, Vol. 7, No. 2, 01.06.2019, p. 180-195.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{8d929abb175c49b687e7697616b755f5,
title = "Influence of measurement errors on networks: Estimating the robustness of centrality measures",
abstract = "Most network studies rely on a measured network that differs from the underlying network which is obfuscated by measurement errors. It is well known that such errors can have a severe impact on the reliability of network metrics, especially on centrality measures: a more central node in the observed network might be less central in the underlying network. Previous studies have dealt either with the general effects of measurement errors on centrality measures or with the treatment of erroneous network data. In this paper, we propose a method for estimating the impact of measurement errors on the reliability of a centrality measure, given the measured network and assumptions about the type and intensity of the measurement error. This method allows researchers to estimate the robustness of a centrality measure in a specific network and can, therefore, be used as a basis for decision-making. In our experiments, we apply this method to random graphs and real-world networks. We observe that our estimation is, in the vast majority of cases, a good approximation for the robustness of centrality measures. Beyond this, we propose a heuristic to decide whether the estimation procedure should be used. We analyze, for certain networks, why the eigenvector centrality is less robust than, among others, the pagerank. Finally, we give recommendations on how our findings can be applied to future network studies.",
keywords = "Business informatics, centrality measures, measurement error, missing data, robustness",
author = "Christoph Martin and Peter Niemeyer",
year = "2019",
month = jun,
day = "1",
doi = "10.1017/nws.2019.12",
language = "English",
volume = "7",
pages = "180--195",
journal = "Network Science",
issn = "2050-1242",
publisher = "Cambridge University Press",
number = "2",

}

RIS

TY - JOUR

T1 - Influence of measurement errors on networks

T2 - Estimating the robustness of centrality measures

AU - Martin, Christoph

AU - Niemeyer, Peter

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Most network studies rely on a measured network that differs from the underlying network which is obfuscated by measurement errors. It is well known that such errors can have a severe impact on the reliability of network metrics, especially on centrality measures: a more central node in the observed network might be less central in the underlying network. Previous studies have dealt either with the general effects of measurement errors on centrality measures or with the treatment of erroneous network data. In this paper, we propose a method for estimating the impact of measurement errors on the reliability of a centrality measure, given the measured network and assumptions about the type and intensity of the measurement error. This method allows researchers to estimate the robustness of a centrality measure in a specific network and can, therefore, be used as a basis for decision-making. In our experiments, we apply this method to random graphs and real-world networks. We observe that our estimation is, in the vast majority of cases, a good approximation for the robustness of centrality measures. Beyond this, we propose a heuristic to decide whether the estimation procedure should be used. We analyze, for certain networks, why the eigenvector centrality is less robust than, among others, the pagerank. Finally, we give recommendations on how our findings can be applied to future network studies.

AB - Most network studies rely on a measured network that differs from the underlying network which is obfuscated by measurement errors. It is well known that such errors can have a severe impact on the reliability of network metrics, especially on centrality measures: a more central node in the observed network might be less central in the underlying network. Previous studies have dealt either with the general effects of measurement errors on centrality measures or with the treatment of erroneous network data. In this paper, we propose a method for estimating the impact of measurement errors on the reliability of a centrality measure, given the measured network and assumptions about the type and intensity of the measurement error. This method allows researchers to estimate the robustness of a centrality measure in a specific network and can, therefore, be used as a basis for decision-making. In our experiments, we apply this method to random graphs and real-world networks. We observe that our estimation is, in the vast majority of cases, a good approximation for the robustness of centrality measures. Beyond this, we propose a heuristic to decide whether the estimation procedure should be used. We analyze, for certain networks, why the eigenvector centrality is less robust than, among others, the pagerank. Finally, we give recommendations on how our findings can be applied to future network studies.

KW - Business informatics

KW - centrality measures

KW - measurement error

KW - missing data

KW - robustness

UR - http://www.scopus.com/inward/record.url?scp=85070406775&partnerID=8YFLogxK

U2 - 10.1017/nws.2019.12

DO - 10.1017/nws.2019.12

M3 - Journal articles

AN - SCOPUS:85070406775

VL - 7

SP - 180

EP - 195

JO - Network Science

JF - Network Science

SN - 2050-1242

IS - 2

ER -

Documents

DOI

Recently viewed

Publications

  1. A PD Fuzzy Control of a Nonholonomic Car-Like Robot for Drive Assistant Systems
  2. Maschinenbelegungsplanung mit evolutionären Algorithmen
  3. Time for the Environment: The Tutzing Time Ecology Project
  4. Mathematik als Fremdsprache?
  5. Papers from the 10th Lancaster University Postgraduate Conference in Linguistics and Language Teaching 2015
  6. Conceptualizing sustainable consumption
  7. Negotiating boundaries through reality shows
  8. A Theory-Based Concept for Fostering Sustainability Competencies in Engineering Programs
  9. "to expose, to show, to demonstrate, to inform, to offer. Artistic Practices around 1990"
  10. The development of an eco-label for software products
  11. “The whole is greater than the sum of its parts” – Exploring teachers’ technology readiness profiles and its relation to their emotional state during COVID-19 emergency remote teaching
  12. Innovative approaches in mathematical modeling
  13. Requests in Informal Conversations
  14. Risk Aversion and Sorting into Public Sector Employment
  15. A panel cointegration rank test with structural breaks and cross-sectional dependence
  16. Processability of Mg-Gd Powder via Friction Extrusion
  17. Risk preferences under heterogeneous environmental risk
  18. § 350
  19. “Regrets for leaving the ‘zoo’?”:
  20. ‘Then you just have to perform better’
  21. A plea for a behavioural approach in the science of human resources management
  22. Thermochemical heat storage materials
  23. Erratum to 5 Development of competencies across the life span
  24. Understanding Societies from Inside the Organisms
  25. Innovativeness and initiative as mediators between achievement orientation and venture performance
  26. Arbeitsvertrag, befristeter
  27. Mythos
  28. Development of an experimental device allowing plant-plant interaction studies and in situ dynamic trapping of volatile organic compounds emitted by barley (Hordeum distichon L.) roots