Seminar by Prof. Xu HAN from Department of Economics and Finance, City University of Hong Kong

This paper investigates the impact of structural breaks in the factor structure on factor-augmented forecasting. We decompose the break in the factor loading matrix into rotational and shift components. To effectively utilize the pre-break data and maintain robustness against shift breaks, we propose a new factor estimator that minimizes the L2 distance between pre- and post-break loading matrices through the rotation of factor estimates. We call this estimator the “rotated factors” and analyze its asymptotic properties, along with two competing factor estimators, in the presence of different types of breaks. We show that the rotated factor is more robust to shift breaks than factors estimated by conventional full-sample PCA. To leverage the respective advantages of each factor estimator in an automatic data driven way, we introduce a method that averages over sets of competing factor estimates using a leave-h-out cross-validation criterion. Simulations demonstrate that combining different factor estimates through the proposed cross-validation averaging approach leads to improved forecasting performance compared to existing methods. Furthermore, we evaluate the effectiveness of our methods in an empirical application with US macroeconomic data and emphasize the importance of incorporating structural breaks into factor-augmented forecasting models.

Xu Han is an associate professor at the Department of Economics and Finance, City University of Hong Kong. He obtained the Bachelor degree from Remin University in 2007, and PhD in Economics from the North Carolina State University in 2012. His research interests are on econometric theories and applied econometrics, especially in high dimensional modeling and big data. Xu has published many papers at top econometric journals, such as Journal of Econometrics, Econometric Theory and JBES.