【摘要】：鑒于股票波動(dòng)具有顯著的多尺度特征,本文引入二元經(jīng)驗(yàn)?zāi)B(tài)分解(EMD)與二元CopulaGARCH算法,提出一種新的VaR風(fēng)險(xiǎn)度量模型,即BEMD-Copula-GARCH模型.具體地,新BEMD-Copula-GARCH模型可分為三個(gè)主要步驟:數(shù)據(jù)分析,分風(fēng)險(xiǎn)估計(jì)和總風(fēng)險(xiǎn)集成.首先,基于二元EMD模型,將復(fù)雜且相互作用的股票對(duì)分解為若干組較為簡(jiǎn)單且相互獨(dú)立的分量,以降低建模難度.其次,引入二元Copula-GARCH模型,刻畫(huà)各組分量間的相互關(guān)系,以度量股票投資組合在不同尺度上的分VaR值.最后,集成各分VaR值以得出最終VaR風(fēng)險(xiǎn)度量結(jié)果.實(shí)證研究以恒生指數(shù)與上證綜指為數(shù)據(jù)樣本構(gòu)造投資組合,結(jié)果表明:本文所構(gòu)建的新模型能有效度量投資組合風(fēng)險(xiǎn),其估計(jì)精度顯著優(yōu)于DCC-GARCH和Copula-GARCH等現(xiàn)有模型.
[Abstract]:In view of the remarkable multi-scale characteristics of stock volatility, this paper introduces binary empirical mode decomposition (EMD) and binary CopulaGARCH algorithm, and proposes a new VaR risk measurement model, that is, BEMD-Copula-GARCH model. Specifically, the new BEMD-Copula-GARCH model can be divided into three main steps: data analysis, risk estimation and total risk integration. Firstly, based on the binary EMD model, the complex and interacting stock pairs are decomposed into some simple and independent components to reduce the difficulty of modeling. Secondly, a binary Copula-GARCH model is introduced to describe the relationship between each group of components to measure the VaR value of the stock portfolio on different scales. Finally, the VaR values are integrated to get the final VaR risk measurement results. The empirical study takes Hang Seng Index and Shanghai Composite Index as data samples to construct a portfolio. The results show that the new model can effectively measure portfolio risk and its estimation accuracy is significantly better than that of existing models such as DCC-GARCH and Copula-GARCH.
【作者單位】： 北京化工大學(xué)經(jīng)濟(jì)管理學(xué)院;北京航空航天大學(xué)經(jīng)濟(jì)管理學(xué)院;湖南科技大學(xué)商學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(71433001,71301006,71201054)~~
【分類(lèi)號(hào)】：F830.91

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 羅俊鵬;;基于Copula的金融市場(chǎng)的相關(guān)結(jié)構(gòu)分析[J];統(tǒng)計(jì)與決策;2006年16期

2 孫志賓;;混合Copula模型在中國(guó)股市的應(yīng)用[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2007年20期

3 李娟;戴洪德;劉全輝;;幾種Copula函數(shù)在滬深股市相關(guān)性建模中的應(yīng)用[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2007年24期

4 王s，

本文編號(hào)：2274691