講座主題：Fast Estimation of a Large TVP-VAR Model with Score-Driven Volatilities

主講嘉賓：鄭挺國，廈門大學bevictor伟德官网和王亞南經濟研究院教授

講座時間：2022年12月08日 14:00-16:00

講座地點：騰訊會議ID 736268185

嘉賓簡介：鄭挺國，廈門大學bevictor伟德官网和王亞南經濟研究院教授、博士生導師，廈門大學特聘教授，主要從事宏觀經濟與政策分析、宏觀計量學、金融計量學、時間序列分析等領域的研究。近年來在Journal of Econometrics、Journal of Business & Economic Statistics、Journal of Multivariate Analysis、Journal of Time Series Analysis等國際學術期刊發表論文近20篇，在《經濟研究》、《經濟學季刊》、《世界經濟》、《金融研究》等國内學術期刊上發表論文50餘篇。曾主持國家自然科學基金項目三項，獲全國優秀博士學位論文提名獎，入選國家級高層次人才、國家萬人計劃青年拔尖人才、福建省哲學社會科學領軍人才、教育部新世紀優秀人才等。

内容摘要：This paper proposes a fast approach for estimating a large time-varying parameter structural vector autoregressive (TVP-SVAR) model. Based on the score-driven modeling framework, we firstly assume that the time-varying variances of structural errors in each equation of the TVP-SVAR are score-driven, and then propose the filtering and smoothing procedures for estimating time-varying parameters and time-varying volatilities. We show that under the forgetting factors, the filtering estimation of time-varying parameters is equivalent to an equation-by-equation estimator, which can significantly reduce the dimension of state space and thus is a very fast estimation. Moreover, an extremely fast smoothing estimation can be derived straightforwardly, overcoming the inverse of the supra-high dimensional state equation covariance matrix. We provide dynamic model averaging (selection) and maximum likelihood estimates for the needs of forecasting and inference, respectively. Our simulation study shows that the proposed method is more accurate than the existing popular methods and illustrates the tremendous computational gain from the equation-by-equation estimator. Finally, we conduct an empirical study on the dynamic connectedness of global stock markets, demonstrating our method's advantages in real-time and ex-post analysis.