基于GARCH族模型的深证成分指数波动性研究

基于GARCH族模型对深证成分指数的波动性进行实证研究。用学生-t分布的GARCH(1,1)模型分析了尖峰厚尾和波动聚集特征,用基于CED分布的GARCH-M(1,1)模型研究了风险溢价情况,以及用基于标准正态分布的EGARCH(1,1)模型分析股市波动的杠杆效应。结果显示,残差确实存在异方差性,股市中收益与风险成正比,同等单位的利空消息对股市冲击更大。最后根据实证研究给出结论与建议。     

考虑结构性变点的股指收益波动性建模

考虑到异方差及波动性突变问题,本文使用带结构性变点虚拟变量的GARCH类模型对近十年的上证指数收益序列进行拟合.结果表明,将虚拟变量加入EGARCH(1,1)模型的拟合效果相对较好,其中,假定扰动项t分布下的拟合优度最高,但GED分布假设下预测精度更好.     

基于GARCH模型的证券投资基金VaR计算与实证研究

基于统计技术的度量金融市场风险值VaR(Value at Risk)己成为测量市场风险的新标准和新方法。鉴此,如何高效、准确的进行VaR的计算将是问题所在。本文基于GARCH模型,讨论了对数收益率时间序列在正态、学生t和广义误差(GED)三种不同分布下的VaR计算方法,并对样本基金的市场风险进行估计,并通过返回检验来检验模型的准确性。研究结果表明,相比之下,基于GED分布的GARCH模型计算的VaR值最能真实地反映基金风险。     

基于GARCH族模型的深圳成指实证分析

通过分析深圳成指日收益率数据,发现其具有尖峰厚尾、非正态性、波动率集聚、自相关性和平稳性等特征。然后将收益率均值方程设定为AR(15)的形式,并假设标准残差服从t分布或GED分布,之后通过实证比较,发现在20种GARCH族模型中,EGARCH(1,1)-M-GED模型是最佳的。最后,本文进行了小结。     

基于VaR-GARCH模型对证券投资基金风险的实证研究

根据证券投资基金收益率序列的尖峰厚尾特征,建立估计基金风险的VaR—GARCH模型。在正态分布、t分布及GED分布三种不同的分布假设下,对基金的VaR值进行估计,并应用Kupiec失败频率检验方法对VaR模型的准确性进行了返回检验。研究结果表明,相比之下,基于GED分布的GARCH模型计算的VaR值最能真实地反映基金风险。     

基于GARCH模型的上证指数与GDP波动性研究

中国的证券市场与宏观经济关系已进入弱相关阶段,本文通过使用ADF检验、ARCH效应检验、GARCH模型分析以及Granger检验对两者的波动性进行分析和研究。实证结果发现,中国的证券市场与宏观经济都具有非正态分布的特性。其次,证券市场不存在自回归条件异方差效应波动,宏观经济存在自回归条件异方差效应波动,并且GARCH(1,1)最适合描述宏观经济的自回归条件异方差效应波动,上证指数的预测与宏观经济的预测两者之间具有互相印证的关系。     

中小企业板市场波动性的实证分析

我国中小板股票市场自2004年启动以来,为中小企业融资起到重要作用。基于中小企业板市场影响因素多、投资风险高、研究不足的现状,文章通过建立GARCH类模型对中小板市场收益率波动性进行实证分析及比较,结果说明GARCH(1,1)模型更适合模拟中小板市场波动性的表现。实证结果表明当前中小板市场处于非理性状态,政府调控无力,众多中小投资者盲目跟风操作,总体投资风险很大。     

基于GARCH模型的VaR方法在沪深300ETF风险测量的应用

交易所交易基金(ETF)在国际社会上被认为是长线投资、价值投资，规避风险的良好金融工具。中国股市投机炒作风气历来盛行，因此在投资领域有必要增强投资者对ETF的认知度和接受度。选用嘉实沪深300ETF作为研究对象，其所追踪的沪深300指数覆盖面广，基本体现中国沪深两市股市的收益状况。从其风险入手，运用GARCH模型研究分析得出该基金收益率的有效条件方差并结合VaR方法准确测量其风险价值，最终确定在95%的置信水平下GARCH(2,1)-t-分布模型能够最佳度量其风险价值。     

我国证券投资基金风险的实证研究

根据证券投资基金收益率序列的尖峰厚尾特征,建立估计基金风险的VaR-GARCH模型。在正态分布、t分布及GED分布三种不同的分布假设下,对基金的VaR值进行估计,并应用Kupiec失败频率检验方法对VaR模型的准确性进行了返回检验。研究结果表明,相比之下,基于GED分布的GARCH模型计算的VaR值最能真实地反映基金风险。     

风险度量的混合GARCH模型及对中国股市的实证分析

基于GARCH模型的VaR计算方法一直是一个颇受关注的研究领域,但在残差服从正态分布的假设下,有时GARCH模型的"尾"仍不够厚.论文讨论了混合广义自回归条件异方差(MGARCH)模型,它能够更好地刻画金融时间序列的厚尾现象.论文还结合我国股市数据,运用EM算法对收益率序列建立混合GARCH模型,计算市场风险VaR值,并对结果做出分析.     

Equity Risk Premium Puzzle: Evidence from Indonesia and Sri Lanka

This paper investigates the equity risk premium puzzle in the Indonesian and Sri Lankan stock markets in order to identify the relationship between the volatility of excess returns and the equity risk premium. The asymmetric impact of negative shocks on the equity risk premium is also examined using threshold and exponential GARCH-M models. We analyse data on the excess returns of the Indonesian and Sri Lankan stock markets from 2004 to 2013, and we find that the impact of the conditional volatility of excess returns on the equity risk premium is not significant in either country. Instead, we find an impact from negative return shocks on the equity risk premium only in Sri Lanka. Therefore, we conclude that investors are not compensated for the conditional volatility of the excess returns in these two markets, while Sri Lankan investors are compensated for the risk of negative shocks.     

上海A、B股市场收益率波动性对比研究及预测

运用GARCH(1,1)-M模型对样本期内上海A、B股市场收益率波动性进行了对比研究及预测。结果显示:上证A、B股指数收益率序列均存在"ARCH/GARCH现象";上海A、B股市场中,期望收益与期望风险正向变动;上海A股市场记忆期长于B股市场;长期中,上海B股市场预期收益将超过A股市场。进一步结合基本面情况可知,上海B股市场具有相对较高的长线投资价值。     

Volatility and Volume in Chinese Stock Markets

The fact that stock market returns in Europe and the USA are characterised by conditional heteroscedasticity is by now well documented in a large literature. We address the question of whether the same is true of the four Chinese stock markets (Shanghai and Shenzhen A and B) over the period from 25 November 1994 to 27 April 2001. Using daily index data, we make two departures from the standard GARCH(1,1) model. First, we use exponential GARCH (EGARCH) to allow for asymmetry in the volatility, which may be present as a result of leverage effects. Second, we respond to evidence of two-way causality between volume and return (and return volatility) by introducing a simultaneous equation model of the relationship. The results of estimating the model indicate that asymmetry does not seem to be present to a significant degree, possibly as a result of lack of information or concern among Chinese investors. We find that volume appears to play a significant part in determining index volatility, which may reflect information arrival effects or may alternatively result from the direct impact of trading on volatility. At the same time, we also find that both the level of returns and their conditional variance have an impact on trade volume, probably because positive (negative) returns tend to attract (deter) investors into the markets.     

中国股市收益率与波动率跳跃性特征的实证分析

股票市场收益率通常小幅波动，但是当市场出现重大或者异常信息时，收益率会在短时间内发生大规模的运动．产生跳跃性变化，市场波动率也明显加剧。本文采用Jump—GARCH对沪深两市A股B股的这类跳跃性特征进行实证分析。根据该模型：当收益率小规模变化时，波动率由GARCH（1，1）平稳随机过程产生，但是当收益率发生跳跃性变化，波动率将背离GARCH（1，1）过程．调整到一个较高的水平。实证结果表明，该模型能够有效地估计出沪深两市收益率和波动率的跳跃性变化．比正态分布的GARCH模型更合理地反应了市场收益率和波动率过程。本文同时讨论了A股B股的跳跃性特征。     

“中小板”市场“牛市”和“熊市”的波动非对称性研究

运用广义误差分布的EGARCH（1,1）模型,分析中小板市场＂牛市＂和＂熊市＂行情（即样本）的波动非对称性。主要结论有：在牛市、熊市中等量＂利好＂消息与＂利空＂消息对股市产生的冲击是不对称的：在牛市中,＂利好＂消息对股市的影响要比相同力度的＂利空＂消息影响大;在熊市中,＂利空＂消息对股市的影响要比相同力度的＂利好＂消息影响大;中小板市场的波动性较大。     

The microstructure of the Chinese stock market

The auction principles, clearance, settlement, and depository (CSD) facilities of the Chinese stock market are described. An autoregressive model is found to characterize the time series properties of stock returns and volatility in the Shanghai market reasonably well. The extremely high volatility of the market is explained well by its lagged volatilities along with trading volumes. Further scrutiny reveals that trading volumes and volatility are endogenous in a vector autoregressive process (VAR) system for the Shanghai Composite Index (SHCI). Foreign shares are found to behave differently from domestic shares in several respects.     

后金融危机时期中国股市的国际地位——基于非线性视角的股市联动网络分析

后金融危机时期全球股市一体化程度不断提高,全面认识中国股市的国际地位对于揭示国际股市一体化联动中的传导机制,防范和应对国际金融风险冲击具有重要的理论意义和现实价值。文章应用非线性格兰杰因果检验方法和社会网络分析方法,对金砖国家和七国集团股市收益率和波动率的联动关系及其联动网络结构进行分析,揭示出中国在国际股市联动中的地位对传导关系的控制方式,定量分析出事件冲击下中国股市与国际股市之间的交互影响。研究发现：（1）国际股市收益率和波动率联动网络呈现出稳定的非线性联动关系网络结构,受其影响各国股市收益之间存在互惠性,而波动之间则存在传染性;（2）在收益率联动网络中,中国股市的作用和地位已与英国相当,远高于其他金砖国家,正逐渐由"从属地位"转向"中心地位";（3）在波动率联动网络中,中国股市是造成国际股市风险交叉影响的重要"桥梁"。综上而言,当前中国股市表现出"高风险低收益"的市场特征;（4）中国对国际股市的影响具有典型的"地缘特征",将网络中心国家股市的利好传递给地缘临近国家股市;（5）波动率联动网络中初始冲击强度较大的国家,往往是对中国股市持续大规模产生冲击的国家;（6）相比较国际股市调整波动冲击的时间而言,中国股市调整时间较短,这表明后金融危机时代中国致力于股市的一系列改革举措取得了显著成效。     

Examining Volatility Persistence and News Asymmetry in Soybeans Futures Returns

Four alternative generalized autoregressive conditional heteroscedasticity (GARCH), and three asymmetric GARCH models (EGARCH, TGARCH and APARCH) are used to examine the presence of volatility persistence and news asymmetry in soybeans futures data. Presence of fat tails in the data series resulted in applying Student’s-t and generalized error distributions in addition to Gaussian normal distribution. The results reveal that soybean return series exhibit volatility characteristics typical of a financial time series. The findings of this study indicate that the leverage effect was absent for soybeans suggesting that positive news causes more volatility to the commodity than negative news. Results further suggest that the fit of the GARCH models is improved by applying t-distribution errors. The diagnostic tests reveal that GARCH models are correctly specified and among all the competing models, APARCH (1,3) model with t-distribution performed best in capturing the volatility.     

Volatility Spillovers between the US and China Stock Markets: Structural Break Test with Symmetric and Asymmetric GARCH Approaches

Abstract

The paper examines the short-run spillover effects of daily stock returns and volatilities between the Standard & Poor's (S&P) 500 stock index in the US and the Shanghai Stock Exchange (SSE) index in China. First, we find that a structural break occurred in the SSE stock return mean in December 2005. Second, by analyzing modified general autoregressive conditional heteroscedasticity (GARCH)(1,1)-M models, we find evidence of a symmetric and asymmetric volatility spillover effect from the US to the China stock market in the post-break period. Third, we observe the symmetric volatility spillover effect from China to the US in the post-break period.