FBA-APAEM Joint Seminar Series

Cointegration Between Two Intrinsically Stationary Spatial Processes

Prof. Qiwei Yao
Chair in Statistics,
Department of Statistics

London School of Economics and Political Science

Date: 06 May 2025 (Tuesday)
Time: 10:30-12:00
Venue: E22-G015
Host: Prof. Degui LI, Distinguished Professor of Business Economics

Abstract
The concept of the intrinsic processes proposed by Matheron (1973) provides an elegant mathematical framework for modelling nonstationary spatial phenomena. It can be viewed as a direct analogue of taking differences of nonstationary time series to achieving stationarity. But it is applicable to spatial data observed on irregular grids. The goal of this paper is to establish the inference methods and the relevant theory for identifying the cointegration between two simple intrinsic processes. We apply the least squares estimation, similar to Engle and Granger (1987). However, the asymptotic property of the estimation is much more complex, depending on the underlying processes as well as the manner in which the observations were taken. We propose some bootstrap approximations for the asymptotic distribution of the estimators. It turns out that the wild bootstrap procedure is adaptive automatically to varying convergence rates under the different schemes of taking the observations. Therefore, it paves the way for constructing practically feasible confidence intervals for cointegration coefficients. A new and easy-to-use statistical tests is constructed for testing the cointegration.

Speaker
Prof. Qiwei Yao is a Chair in Statistics at London School of Economics and Political Science. He is an internationally renowned statistician and has been engaged in teaching and research statistics. Prof. Yao’s main research areas include time series analysis, spatial-temporal models and financial econometrics. He has published 2 books and 90+ research articles in leading journals in statistics and econometrics such as Annals of Statistics, Econometrica, Journal of the American Statistical Association, Journal of Royal Statistical Society (Series B) and Journal of Econometrics. He served as the Joint Editor of Journal of Royal Statistical Society (Series B) and Associate Editor of top journals such as Annals of Statistics and Journal of the American Statistical Association, and is a Fellow of Institute of Mathematical Statistics and American Statistical Association and an elected member of International Statistical Institute.

All are welcome!