【学术讲座】Are Bond Returns Predictable with Real-Time Macro Data?

发布者:统计与数据科学学院发布时间:2022-10-11浏览次数:1141

【专家简介】李鲲鹏,现为首都经济贸易大学国际经管学院教授、博士生导师、院长,研究领域为大数据计量经济学,包括高维因子分析、交互效应分析、空间网络模型与门限断点模型,在国内外主流期刊发表论文30余篇,主持国家自然科学基金四项、参与国家社科基金一项,目前是Journal of Business & Economic Statistics期刊编委、《计量经济学报》编委、《经济与管理研究》编委、管理科学与工程学会金融计量与风险管理分会副理事长、中国数量经济学常务理事。

【报告摘要】We examine whether bond returns  are predictable  by real-time macro variables under possible nonlinear predictive relationship and possible presence of weak factors. We propose a scaled sufficient forecasting method to account for the nonlinearity and weak factors, and study its asymptotic  properties. With both existing methods and our new  approach, we find that real-time macro variables have significant forecasting power both in- and out-of-sample, generate sizeable economic values, and their predictability is not spanned by yield curve. We also find that the forecasted bond returns are countercyclical and the magnitude of predictability is stronger in economic recessions, thereby lending empirical support to well-known macro finance

theories.

腾讯会议号:401 249 889

      间:20221013日(星期四)上午9:00