Bayesian Analysis of CAViaR Model

摘要：

Bayesian inference with Markov chain Monte Carlo simulation to estimate conditional autoregressive value at risk by regression quantiles model (Engle and Manganelli,2004) is recommended based on error item of asymmetric Laplace distribution in quantile equation.For a general quantile-based model,we supply a condition to ensure posterior distributions of estimated parameters are always proper.We prove that scale parameter of asymmetric Laplace distribution should be parameterized and determined through Markov chain Monte Carlo simulation.A new quantile specification in CAViaR framework is used to measure market risk of Hang Seng Index,and empirical analysis suggests our approach is efficient.

关键词： Bayesian inference CAViaR Markov chain Monte Carlo Market risk

作者: Xinyu Wang Qiangyuan Zhang

作者单位: School of Management,China University of Mining and Technology,Xuzhou 221008,P.R.China

会议类型: 国际会议

会议名称: The 2008 International Conference on Business Intelligence and Financial Engineering(BIFE 2008)(商业智能和金融工程国际会议)

会议地点: 长沙

会议语种:英文

页码: 605-610

在线出版日期: 2008-10-28（万方平台首次上网日期，不代表论文的发表时间）