A0843
Title: Network regression and supervised centrality estimation
Authors: Junhui Jeffrey Cai - University of Notre Dame (United States)
Haipeng Shen - The University of Hong Kong (Hong Kong)
Wu Zhu - Tsinghua University (China)
Linda Zhao - University of Pennsylvania (United States)
Ran Chen - Massachusetts Institute of Technology (United States)
Dan Yang - University of Hong Kong (Hong Kong) [presenting]
Abstract: The centrality in a network is often used to measure nodes' importance and model network effects on a certain outcome. Empirical studies widely adopt a two-stage procedure, which first estimates the centrality from the observed noisy network and then infers the network effect from the estimated centrality, even though it lacks theoretical understanding. A unified modeling framework is proposed, under which the shortcomings of the two-stage procedure are first proven, including the inconsistency of the centrality estimation and the invalidity of the network effect inference. Furthermore, a supervised centrality estimation methodology is proposed, which aims to simultaneously estimate both centrality and network effect. The advantages in both regards are proved theoretically and demonstrated numerically via extensive simulations and a case study in predicting currency risk premiums from the global trade network.
