永利集团3044官网欢迎您
WISE
Chow Institute
User Center
Old Version
Chinese
CHINESE
EN
About
About Us
Contact US
People
Faculty Directory
Staff Dirctiory
Program
The Undergraduate Program
The Graduate Program
International Graduate Program
The Part-time Graduate Course Program
Study Aboad Program
Course Catalogue
Research
Publications
Working Papers
News & Events
News
Announcements
Academic Calendar
Seminars
Workshop & Conference
EN
CHINESE
EN
WISE
Chow Institute
User Center
About
About Us
Contact US
People
Faculty Directory
Staff Dirctiory
Program
The Undergraduate Program
The Graduate Program
International Graduate Program
The Part-time Graduate Course Program
Study Aboad Program
Course Catalogue
Research
Publications
Working Papers
News & Events
News
Announcements
Academic Calendar
Seminars
Workshop & Conference
Research
Research
Publications
Working Papers
Research
Publications
Working Papers
Publications
Location:
Home
->
Research
->
Publications
-> Content
基于广义谱和MCS检验的VaR模型预测绩效评估
id: 2320
Date: 20160223
Times:
Magazines
第28卷第4期,P108-119
Author
张玉鹏, 洪永淼
Content
条件VaR 模型的正确设定检验等价于检验均值化的“撞击序列”是否服从鞅差分序 列,然而通常的反馈检验方法只检验了该序列的部分性质。采用对该鞅差分性质进行直接检 验的广义谱检验方法,全面考察中国股票市场( 香港恒生指数、上证综合指数和台湾加权指 数) 上各参数、非参数和半参数共22 个VaR模型在采用滚动窗口预测机制时的样本外预测绩 效。鉴于条件VaR模型正确设定检验无法反映超过某VaR水平的尾部风险信息,为避免极端 损失的发生以及增加结果的稳健性,同时采用模型置信集检验方法。研究结果表明,采用通 常的反馈检验方法常会得出错误的结论; 在1%和5%置信水平,与历史模拟法、极值理论模型、 CAViaR模型和CARE模型相比,误差项为t分布的GARCH模型族在金融危机期间具有较好的样 本外预测绩效; 涨跌停板制度对于选取预测绩效最优的VaR模型具有重要影响。
JEL-Codes
Keywords
VaR模型; 预测绩效; 涨跌停板制度; 广义谱检验; MCS 检验
TOP