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

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

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.

Original languageEnglish
JournalNetwork Science
Volume7
Issue number2
Pages (from-to)180-195
Number of pages16
ISSN2050-1242
DOIs
Publication statusPublished - 01.06.2019

    Research areas

  • Business informatics - centrality measures, measurement error, missing data, robustness

Documents

DOI

Recently viewed

Researchers

  1. Isabel Albrecht

Publications

  1. A Semiparametric Approach for Modeling Not-Reached Items
  2. Assessment of cognitive load in multimedia learning with dual-task methodology
  3. Trees in the desert
  4. Conveying the Ethics of Artificial Intelligence in K–12 and Academia: A Systematic Review of Teaching Methods
  5. Low Resource Question Answering: An Amharic Benchmarking Dataset
  6. Genetically based differentiation in growth of multiple non-native plant species along a steep environmental gradient
  7. End-users’ perspective on digitalization
  8. The self-sabotage of conservation
  9. The Role of Assessment and Quality Management in Transformations towards Sustainable Development
  10. Exploring the motivations of protesters in contingent valuation
  11. Armed to Kill
  12. Web-based guided self-help for employees with depressive symptoms (Happy@Work)
  13. Corrosion behavior and microstructure of a broad range of Mg-Sn-X alloys
  14. A flexible semi-empirical model for estimating ammonia volatilization from field-applied slurry
  15. Conceptual frameworks and methods for advancing invasion ecology
  16. Using Large N Longitudinal Comparison to Explain Political Recruitment in Changing Democracies
  17. Article 3 Universal Application
  18. Walking Text and Writing Space
  19. Nachhaltigkeitsethik
  20. An interpretive perspective on co-production in supporting refugee families’ access to childcare in Germany
  21. Effekte inter-organisationaler Balanced Scorecards
  22. Fremde Töpfe
  23. Virtual-exchange collaboration timeline planner
  24. Fieldwork meets crisis: Introduction
  25. Das Reflexivitätsproblem und die Kategorienlehre
  26. Universität hat Zukunft
  27. Political Representation in the EU
  28. Globalisierung
  29. From the environmental state to the sustainability state? Conceptualization, indicators, and examples
  30. Amtsmenschen
  31. When (and how) ideas become arguments
  32. Fallstudie
  33. How environmental and social orientations influence the funding success of investment-based crowdfunding
  34. Fallstudie
  35. Average wage, qualification of the workforce and export performance in German enterprises: evidence from KombiFiD data
  36. How to measure energy-efficiency of software
  37. Small Particle Size Magnesium in One-pot Grignard-Zerewitinoff-like Reactions under Mechanochemical Conditions
  38. Bifunctional recombinant protein SDF1-GPVI as a new therapeutic concept for improved regeneration
  39. Can't Stop The Feeling
  40. Deformation-induced dynamic precipitation during creep in magnesium-tin alloys
  41. The attenuating effect of mortality salience on dishonest behavior
  42. Entrepreneurship and the "theory of planned behavior"