波动率是对金融时间序列中的不确定性进行定量描述的指标之一，在现代金融市场中，特别是计量经济领域，波动率对有关金融产品和金融衍生产品的交易、定价、风险管理及投资策略等都能产生重大的影响。对波动率进行有效的预测和估计具有十分重要的实践价值和理论意义，因为这将有助于我们加强风险管理，防范金融危机，维持金融市场健康稳定发展。 股票市场作为金融市场的重要组成部分，也是联系其他金融子市场的纽带，股票市场的健康发展对国家经济的发展起到重要的推动作用，波动率是衡量股票市场收益状况的重要指标，因此对股票市场的波动率进行研究尤为迫切。股票市场的联动性和传染性，是它的一大特性之一，这个特性导致股票市场受各方面因素影响的反应尤为强烈。股票市场的波动会发生变结构现象当某一消息（利好或利空）进入市场后的某个时刻，因为这些消息会在某一时刻引发收益发生跳跃式的变化从而导致变结构现象。反过来说，也就是如果股票市场中出现了变结构，那么也就意味着有重大的消息进入了股票市场，这些重大消息会给股票市场中的利益相关者带来极大的影响，进而对金融秩序的稳定性造成影响。当然如果我们在研究股票市场的波动率时忽略了变结构的影响，那么我们对波动率的刻画也会出现偏差，更无法对下一次重大消息进入股市的时点进行预警和预判；如果我们在研究股票市场波动率时考虑变结构的影响，但对变点的位置判断不准确或误判了波动状态，这样不断会降低金融管理者的风险管理水平，更会给投资者带来重大的利益损失。因此为了促进股票市场的健康发展，保护投资者利益，提高管理者的风险管理能力，我们需要对波动率的变结构进行研究。 本文主要利用累积和方法对中国沪、深股票市场的波动变结构现象进行了研究。实证结果表明：（1）上证综指和深证综指都存在明显的波动变结构现象，并且二者的波动变结构具有一致性和相关性。（2）上证综指和深证综指在全样本区间都存在异方差效应且具有显著的波动聚集性，但在去除变结构效应后，二者均没有异方差效应。这表明变结构现象很可能是导致收益率序列产生异方差的原因。

Volatility is one of the indicators that quantitatively describe the uncertainty in financial time series. In the modern financial market, especially in the econometric field, volatility affects the trading, pricing, and risk management of financial products and financial derivatives. Investment strategies can have a significant impact. Effective forecasting and estimation of volatility has very important practical and theoretical value. Because it will help us strengthen risk management, prevent financial crisis, and maintain the healthy and stable development of the financial market. The stock market, as an important part of the financial market, is also the link connecting other financial submarkets. The healthy development of the stock market plays an important role in the development of the national economy. The volatility rate is an important measure of the stock market's return. Therefore, the study of volatility in the stock market is particularly urgent. The linkage and infectivity of the stock market is one of its major characteristics. This characteristic has led to a particularly strong reaction to the stock market due to various factors. The volatility of the stock market can happen when the news (good or bad) enters the market at a certain point in time, because these messages will cause a jump in earnings at some point in time, resulting in a structural change. Conversely, if there is a change in the structure of the stock market, it means that the significant news entering the stock market, which will have a great impact on stakeholders in the stock market. The stability of the financial order has an impact. Of course, if we ignore the effects of variable structure when we study the volatility of the stock market, then we will also have deviations from the characterization of volatility, and it is even more difficult to give early warning and pre-judgment when the next major news enters the stock market; if When studying the volatility of the stock market, consider the impact of variable structure, but inaccurate judgment of the position of the change point or misjudgment of the volatility will continue to reduce the risk management level of financial managers, and it will also bring significant losses to investors. . Therefore, in order to promote the healthy development of the stock market, protect the interests of investors, and improve managers' risk management capabilities, we need to study the variable structure of volatility. In this paper, we used CUSUM method to study the variance structure change of China stock markets. First, we found that the two indices had obvious volatility structure change when we analyzed the return series of Shanghai Composite Index and Shenzhen Composite Index from 2006 to 2016. Then we found that both Shanghai Composite Index and Shenzhen Composite Index have obvious heteroscedasticity and volatility-clustering in the whole samples. But, there is no heteroscedasticity in the two indexes when we removed the effect of structure change. Which show that the structure change is probably the cause of heteroskedasticity in the yield series.