A1148
Title: Monitoring the housing market in real-time with high-dimensional predictors
Authors: Lajos Horvath - University of Utah (USA)
Zhenya Liu - Renmin University of China (China)
Shanglin Lu - University of International Business and Economics (China) [presenting]
Vincent Yao - Georgia State University (United States)
Abstract: A sequential detection procedure for dynamic linear models is employed to monitor the structural breaks in the housing market in real time. We incorporate 127 macroeconomic variables as the driving factors in modeling the changes in the log housing prices to mitigate the estimation bias caused by omitted variables. The principal components are used to shrink the high-dimensional macroeconomic factor space when the training sample size of the monitoring procedure is small. We find that those superstar cities in the U.S. experienced another amplification mechanism phase during the COVID-19 period.