On business cycle forecasting

作     者：Huiwen Lai Eric C.Y.Ng Huiwen Lai;Eric C.Y.Ng

作者机构：School of Accounting and FinanceFaculty of BusinessHong Kong Polytechnic UniversityHong KongChina Department of EconomicsHong Kong University of Science and TechnologyHong KongChina 

出 版 物：《Frontiers of Business Research in China》 (中国高等学校学术文摘·工商管理研究（英文版）)

年 卷 期：2020年第14卷第3期

页      面：324-349页

学科分类：02[经济学] 0202[经济学-应用经济学] 03[法学] 0302[法学-政治学] 020206[经济学-国际贸易学] 030206[法学-国际政治] 020202[经济学-区域经济学] 

基　　金：funding from School of Accounting and Finance Faculty of Business Hong Kong Polytechnic University 

主　　题：Recession forecasting Business cycle Autoregressive Logit Dynamic factor Mixed data sampling(MIDAS)regression 

摘      要：We develop a recession forecasting framework using a less restrictive target variable and more flexible and inclusive specification than those used in the *** target variable captures the occurrence of a recession within a given future period rather than at a specific future point in time(widely used in the literature).The modeling specification combines an autoregressive Logit model capturing the autocorrelation of business cycles,a dynamic factor model encompassing many economic and financial variables,and a mixed data sampling regression incorporating common factors with mixed sampling *** model gene rates significantly more accurate forecasts for *** with smaller forecast errors and stronger early signals for the turning points of business cycles than those gene rated by existing models.