Structural Break Inference in Spatial Autoregressive Models Using GMM
Prof. Ryo OKUI
Professor of Economics
Graduate School of Economics
University of Tokyo
Date: 27 January 2026 (Tuesday)
Time: 10:30-12:00
Venue: E22-G008
Host: Prof. Degui LI, Distinguished Professor in Business Economics
Abstract
This study presents a novel generalized method of moments (GMM) approach for detecting structural breaks in panel-data spatial autoregressive (SAR) models. By using linear moment conditions with peer-to-peer instrumental variables, our approach is more robust to time-varying and heterogeneous error distributions. We develop GMM-based estimation procedures and sup-Wald test statistics for unknown structural breakpoints in SAR models. Monte Carlo simulations demonstrate that our method consistently outperforms existing quasi-maximum-likelihood estimators, especially under time-varying or heteroskedastic error distributions. In an empirical application to U.S. state fiscal data, we analyze fiscal interdependence and provide economic interpretations of the identified breakpoints. This is based on joint work with Hayato Tagawa.
Speaker
Prof. Ryo OKUI is a Professor of Economics at the University of Tokyo. Prior to joining the University of Tokyo, he was an Associate Professor at Seoul National University, NYU Shanghai, and Kyoto University, and was an Assistant Professor at Hong Kong University of Science and Technology. He was also a Visiting Professor at the University of Gothenburg and a Visiting Associate Professor at Vrije Universiteit Amsterdam. He holds a PhD from the University of Pennsylvania and a Bachelor’s in Economics from Kyoto University. His work has appeared in Econometrica, the Review of Economic Studies, and the Journal of Econometrics, among other outlets. Professor Okui is a recipient of the Nakahara Prize from the Japanese Economic Association and the Research Achievement Award and the Ogawa Research Prize from the Japan Statistical Society.
All are welcome!
