Cookies?
Library Header Image
LSE Research Online LSE Library Services

On the consequences of power-law behavior in partial correlation network models

Barigozzi, Matteo, Brownlees, Christian and Lugosi, Gabor (2018) On the consequences of power-law behavior in partial correlation network models. Electronic Journal of Statistics, 12 (2). pp. 2905-2929. ISSN 1935-7524

[img]
Preview
Text - Accepted Version
Download (1MB) | Preview

Identification Number: 10.1214/18-EJS1478

Abstract

We introduce a class partial correlation network models whose network structure is determined by a random graph. In particular in this work we focus on a version of the model in which the random graph has a power-law degree distribution. A number of cross-sectional dependence properties of this class of models are derived. The main results we establish is that when the random graph is power-law, the system exhibits a high degree of collinearity. More precisely, the largest eigenvalues of the inverse covariance matrix converge to an affine function of the degrees of the most interconnected vertices in the network. The result implies that the largest eigenvalues of the inverse covariance matrix are approximately power-law distributed, and that, as the system dimension increases, the eigenvalues diverge. As an empirical illustration we analyse a panel of stock returns of a large set of companies listed in the S&P500 and show that the covariance matrix of returns exhibits empirical features that are consistent with our power-law model.

Item Type: Article
Official URL: https://projecteuclid.org/info/euclid.ejs
Additional Information: © 2018 The Authors
Divisions: Statistics
Subjects: Q Science > QA Mathematics
Date Deposited: 11 Sep 2018 14:41
Last Modified: 13 Sep 2024 13:21
URI: http://eprints.lse.ac.uk/id/eprint/90200

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics