Asymptotics in the β-model for networks with a differentially private degree sequence. Issue 18 (16th September 2020)

• Record Type: Journal Article
• Authors: Pan, Lu; Yan, Ting
• Is Part Of: Communications in statistics. Volume 49:Issue 18(2020)
• Page Start: 4378
• Page End: 4393
• Publication Date: 2020-09-16
• Subjects: Asymptotic normality -- consistency -- degree -- differential privacy; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2019.1599023
• Languages: English
• ISSNs: 0361-0926

Abstract

Abstract: The β -model is a natural model for characterizing the degree heterogeneity that widely exists in the network data. The estimators of the model parameters in the differentially private β -model with the denoised process have been shown to be consistent and asymptotically normal. In this paper, we show that the moment estimators of the parameters based on the differentially private degree sequence without the denoised process is consistent and asymptotically normal.