Speaker: Dr. 杨乔 (Qiao Yang)

Title: A GARCH with Infinite Hidden Markov Model to Short-term T-Bill Rate

Schedule: Dec 17, 1:30-3:00PM

Location: 诚明楼 (Chengming Hall), Rm 315

Introduction: 杨乔, 上海科技大学创业与管理学院常任副教授。2010年毕业于加拿大女皇大学，取得经济学优秀荣誉学士学位，2016年毕业于加拿大多伦多大学，取得经济学博士学位。主要研究领域为贝叶斯计量，时间序列模型预测，金融计量。 成果在Journal of Econometrics, Journal of Applied Econometrics, International Journal of Forecasting, Journal of Empirical Finance, Journal of Forecasting等期刊发表。主持国家自然科学基金青年项目。现为上海数量经济学会理事。

Abstract: The time-series dynamics of short-term interest rates are important because they are a key input into pricing models of the term structure of interest rates. In this paper, we extend the infinite hidden Markov models to include a GARCH component to jointly model the volatility of interest rates. In this way, the volatility can consist of both structural and persistent changes. Applied to monthly U.S. data, we find significant parameter changes over time and strong evidence of non-Gaussian conditional distributions. Our new model provides significant improvements in both density forecasts and point forecasts. We find evidence of volatility dynamics in the empirical application.