:::

Data-driven Estimation Window for Forecasting with Factor Structure


  • 研討會日期 : 2021-04-27
  • 時間 : 14:30
  • 主講人 : Professor Shou-Yung Yin (殷壽鏞)
  • 主持人 : Professor Chun-Che Chi
  • 地點 : Conference Room B110
  • 演講者簡介 : Professor Yin received his Ph.D. in Economics from National Central University in 2013. He is currently an Assistant Professor at National Taipei University. His research fields are Econometric theory (Panel data model, factor model, time series analysis) and empirical monetary economics.
  • 演講摘要 : This paper considers a reversed order monitoring cusum (ROM) type procedure with the factor structure for improving the forecast performance. Despite detecting the latest break, we allow the unobserved factors as predictors. Two algorithms are proposed for dealing with latent predictors. We show that these estimated factors would not change the asymptotic property of the Brownian motion under regular conditions with a suitable ratio of N to T. Monte Carlo simulations show that there is almost no size distortion, and the power is promising when we extend the evaluating time period by using estimated factors. We also use the simulation to compare the proposed procedure with the fixed windows approach, and the results reveal that the ROM approach, in general, dominates the fixed window method. We then apply the ROM method to predict the monthly growth rate of the U.S. house prices. The results support that using the ROM method can improve the out-of-sample forecast compared to other weighted approaches.