报告题目 | Assessing Tail Risk via A Generalized Conditional Autoregressive Expectile Model | ||
报告人（单位） | 方 颖教授 厦门大学 | ||
点评人（单位） | 刘晓星教授 （东南大学） | 点评人（单位） | |
时间地点 | 会议时间：2023/6/9（周五）16：00 地点：经管楼B201 | ||
报告内容摘要： This paper proposes a generalized conditional autoregressive expectilemodel, including autoregressive components in assessing tail risk, which can betreated as an infinite version of the conditional autoregressive expectile modelproposed by Kuan, Yeh and Hsu (2009) and can be implemented as a vehicle forestimating the conditional autoregressive Value-at-Risk by regression quantiles modelproposed in Engle and Manganelli (2004) and studied by Xiao and Koenker (2009).Due to the unobservable latent components in the proposed model, thequasi-maximum likelihood estimation method is suggested for estimating the relevantparameters, and a heteroskedasticity and autocorrelation consistent covariancematrix estimator is proposed. Furthermore, a dynamic expectile test is proposed forboth in-sample model adequacy evaluation and out-of-sample forecasting forcomparison purposes. Finally, Monte Carlo simulations and applications to real dataare conducted to illustrate that the proposed methodology is practically useful.Particularly, our empirical study demonstrates that the tail risk characterized by theproposed model achieves a better performance, especially in the period of theCovid-19 epidemic. | |||
报告人简介：
方颖，厦门大学校长助理，厦门大学王亚南经济研究院与经济学院统计学与数据科学系教授，主要从事计量经济学理论与方法研究及其在宏观经济学、金融学、环境经济学和社会经济政策评估等领域的应用，在《经济研究》和Journal of Econometrics等学术期刊发表学术论文近50余篇，创新和丰富工具变量模型、函数系数模型以及面板数据分位数模型在经济和金融领域的估计与检验方法，获得国家杰出青年科学基金资助，担任第八届统计学国务院学科评议组成员。 | |||
