Economic forecasts using many noise
使用很多噪音的经济预测
主讲人：Yuan Liao（Rutgers University）
主持老师：（北大经济学院）王法
参与老师：（北大经院）王一鸣、王熙、刘蕴霆
（北大国发院）黄卓、张俊妮、孙振庭
（北大新结构）胡博
时间：2024年3月8日（周五）10:00-11:30
地点（线上）：Join Zoom Meeting
https://us06web.zoom.us/j/83439888568?pwd="Lly0a7qOc0NAP90Kj8t2VH4IBWD3kH.1
Meeting ID: 834 3988 8568 Passcode: 321668
报告摘要：
This paper addresses a key question in economic forecasting: does pure noise truly lack predictive power? Economists typically conduct variable selection to eliminate noises from predictors. Yet, we prove a compelling result that in most economic forecasts, the inclusion of noises in predictions yields greater benefits than its exclusion. Furthermore, if the total number of predictors is not sufficiently large, intentionally adding more noises yields superior forecast performance, outperforming benchmark predictors relying on dimension reduction. The intuition lies in economic predictive signals being densely distributed among regression coefficients, maintaining modest forecast bias while diversifying away overall variance, even when a significant proportion of predictors constitute pure noises. One of our empirical demonstrations shows that intentionally adding 300~6,000 pure noises to the Welch and Goyal (2008) dataset achieves a noteworthy 10% out-of-sample R square accuracy in forecasting the annual U.S. equity premium. The performance surpasses the majority of sophisticated machine learning models.
主讲人简介：
Yuan Liao is a Professor of Economics specializing in Econometrics. He works at the intersection of financial econometrics and statistics. He received his Ph.D. in Statistics from Northwestern University in 2010. Before joining Rutgers, Yuan held a position as Assistant Professor of Statistics at University of Maryland (2012-2016), and worked at Princeton University as a postdoctoral associate (2010-2012). He is currently associate editor of Journal of Econometrics and JASA.
