On the Propagation of Uncertainty in Network Inference to Network Characterization

• Activity Number: 629
• Type: Contributed
• Date/Time: Thursday, August 5, 2010 : 8:30 AM to 10:20 AM
• Sponsor: ENAR
• Author(s): Eric Kolaczyk*+ and Weston Viles
• Companies: Boston University and Boston University

Abstract

Network-based data (e.g., from sensor, social, biological, and information networks) now play an important role across the sciences. Frequently the graphs used to represent networks are inferred from data. Surprisingly, however, in characterizing the higher-level properties of these networks (e.g., density, clustering, centrality), the uncertainty inherent in their inferred topology typically is ignored. We explore the problem of estimating network density - a simple but fundamental characterization of a network - in the context of correlation networks with Gaussian noise. Motivated by the observation that estimators defined implicitly through standard thresholding procedures can be substantially biased, we propose a new estimator, and show that it is asymptotically unbiased and possessed a central limit theorem that allows for construction of asymptotic confidence intervals.