Academic Events

Weining Wang

University of Bristol

This paper analyzes spillover effects in spatial (network) models when measurement noise might contaminate the neighborhood (i.e. adjacency) matrix. We propose to adopt a low-rank and sparse structure to capture stylized network patterns in empirical datasets. We develop a flexible estimation framework via regularization techniques: a Least Absolute Shrinkage and Selection Operator (LASSO) penalty for the sparse component and a nuclear norm penalty for the low-rank component. We propose two estimators: (1) A two-stage procedure that first de-noises the adjacency matrix via regularization and subsequently integrates the purified network into a regression analysis, and (2) A single-step supervised Generalized Method of Moments (GMM) estimator that jointly estimates the regression parameters and refines the network structure. Simulation evidence underscores the superiority of our approach relative to conventional estimation protocols. In scenarios with noisy networks, our method reduces the root mean squared error (RMSE) of the estimate of spillover effects by 50–70% compared to conventional GMM. This advantage is more significant when measurement errors are correlated with the observed outcomes and network contamination is econometrically endogenous. We apply our framework to the dataset in Besley and Case (1995) and demonstrate its practical utility. The decomposition not only improves estimation reliability but also generates granular insights for policy design. These results highlight that we can bridge the gap between methodological rigor and policy relevance by explicit modeling of network structure heterogeneity.

JEL Classification: C21, C23, D57

Keywords: network analysis, policy effects, LASSO, nuclear norm penalty, penalized GMM

Dr Weining Wang is currently a Professor of Economics at the University of Bristol.

Dr Weining Wang was a Chair Professor in Econometrics at the University of Groningen, Faculty of Economics and Business. Dr. Weining Wang was a Chair Professor in Financial Econometrics in the Department of Economics and Related Studies at the University of York, UK. She received a Doctor Degree in Economics from Humboldt University in Berlin. Her research fields mainly include non-parametric and semi-parametric econometrics, high-dimensional econometrics, network models, and time series. She published in several top journals in the areas, including Annals of Statistics, Journal of Business & Economic Statistics, Journal of Econometrics, Journal of the American Statistical Association, Econometric Theory, and others. Her research mainly focuses on panel data, high-dimensional time series models, and other applied econometrics methods. The goal is to address specific economic and financial research questions, such as system risk model analysis, financial derivatives asset pricing, and social network analysis.