Riemann manifold Langevin methods on stochastic volatility estimation

被引:1
|
作者
Zevallos, Mauricio [1 ]
Gasco, Loretta [2 ]
Ehlers, Ricardo [3 ]
机构
[1] Univ Estadual Campinas, Dept Stat, UNICAMP, Campinas, SP, Brazil
[2] Pontificia Univ Catolica Peru, Fac Ciencias & Ingn, San Miguel Lima, Peru
[3] Univ Sao Paulo, Dept Appl Math & Stat, BR-03178200 Sao Paulo, Brazil
基金
巴西圣保罗研究基金会;
关键词
Bayesian analysis; Langevin methods; Markov chain; Monte Carlo; Metropolis-Hastings; Value at Risk; T-DISTRIBUTION; MODELS;
D O I
10.1080/03610918.2016.1255972
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this article, we perform Bayesian estimation of stochastic volatility models with heavy tail distributions using Metropolis adjusted Langevin (MALA) and Riemman manifold Langevin (MMALA) methods. We provide analytical expressions for the application of these methods assess the performance of these methodologies in simulated data, and illustrate their use on two financial time series datasets.
引用
收藏
页码:7942 / 7956
页数:15
相关论文
共 50 条