Assist. Prof. Ulrich Müller

“Forecasting Related Time Series”

A collection of time series are “related” if they follow similar stochastic processes and/or they are statistically dependent. In this article, forthcoming in the Journal of Applied Econometrics, Ulrich K. Müller and Mark Watson propose a Related Time Series (RTS) forecasting model that exploits these relationships. The model’s foundation is a set of univariate Gaussian autoregressions, one for each series, which are then augmented to incorporate stochastic volatility, heavy-tailed innovations, additive outliers, time-varying parameters and common factors. The model is estimated and forecasts are computed using Bayesian methods with hierarchical priors that pool information across series. Computationally efficient MCMC methods are proposed. The RTS model is applied to three datasets and yields encouraging pseudo-out-of-sample forecasting results.

Mr. Müller’s research is in econometric theory with interests in time series and forecasting, cluster dependence, spatial dependence, Bayesian inference and extreme value theory. During his visit at CES he will continue his research, joint with Michal Kolesar, of small sample valid confidence intervals in a linear regression with Gaussian but heteroskedastic or clustered errors. The objective is to derive inference that is small sample valid by appropriately adjusting the critical value from 1.96 to a larger value, inducing small sample conservativeness.

Ulrich Müller is the Stanley G. Ivins ’34 and Henrietta Bauer Ivins Professor in Economics at Princeton University. He received his PhD in Economics at the University of St. Gallen (Switzerland) in 2002 and has been at Princeton since 2003. Mr. Müller is a Fellow of the Econometric Society, a Fellow of the Journal of Econometrics, and a fellow of the International Association of Applied Econometrics, and he served as an associate editor of Econometric Theory, as foreign editor to the Review of Economic Studies and as an associate and co-editor of Econometrica.