本文選題：股票市場(chǎng)　切入點(diǎn)：羊群效應(yīng)　出處：《南京財(cái)經(jīng)大學(xué)》2012年碩士論文

【摘要】：股票市場(chǎng)投資者非理性行為是行為金融研究的重要對(duì)象之一。投資者非理性行為不僅增加了股票市場(chǎng)的波動(dòng)，還會(huì)影響股票市場(chǎng)效率。本文在對(duì)羊群效應(yīng)相關(guān)理論、方法研究的基礎(chǔ)上，探討了羊群行為檢驗(yàn)新方法，并對(duì)股票市場(chǎng)羊群行為檢驗(yàn)的基礎(chǔ)上，，進(jìn)一步研究了市場(chǎng)羊群行為與市場(chǎng)效率的關(guān)系，主要內(nèi)容如下: 一、股票市場(chǎng)羊群效應(yīng)檢驗(yàn)方法的改進(jìn)及深圳股市羊群行為的檢驗(yàn) （1）在綜合CCK、I-CCK以及T-CCK模型的優(yōu)點(diǎn)基礎(chǔ)上，加速考慮市場(chǎng)的異方差效應(yīng)，提出改進(jìn)的羊群效應(yīng)檢驗(yàn)?zāi)Ｐ汀猇-CCK模型； （2）利用改進(jìn)的V-CCK模型，對(duì)深圳股票市場(chǎng)羊群效應(yīng)進(jìn)行檢驗(yàn)，并與已有模型檢驗(yàn)結(jié)果比較，結(jié)果表明，提出的V-CCK模型更優(yōu)； （3）靜態(tài)結(jié)果表明，無(wú)論是股市上漲還是股市下跌，深圳股市都存在顯著的羊群效應(yīng)，但是下跌時(shí)的羊群效應(yīng)強(qiáng)于上漲時(shí)的羊群效應(yīng)；動(dòng)態(tài)結(jié)果表明，隨著時(shí)間的推移，該股市中的羊群效應(yīng)呈現(xiàn)變?nèi)醯内厔?shì)，并且股市下跌時(shí)的羊群效應(yīng)始終強(qiáng)于上漲時(shí)的羊群效應(yīng)。 二、深圳股票市場(chǎng)的羊群效應(yīng)與市場(chǎng)效率的關(guān)系研究 運(yùn)用V-CCK模型和MF-DMA（多重分形移動(dòng)平均消除趨勢(shì)）方法分別提出羊群效應(yīng)指標(biāo)HE和有效性指標(biāo)EFF，利用滑動(dòng)窗技術(shù)，方法分別計(jì)算出羊群效應(yīng)指標(biāo)序列HEt和有效性指標(biāo)序列EEFt。 （1）相關(guān)性檢驗(yàn)發(fā)現(xiàn)，HE和EFF之間存在明顯的正相關(guān)關(guān)系； （2）線性Granger因果關(guān)系檢驗(yàn)結(jié)果表明，HE不是EFF的線性Granger原因，而EFF是HE的線性Granger原因； （3）非線性檢驗(yàn)表明，HE和EFF兩個(gè)變量之間存在明顯的非線性動(dòng)態(tài)變化趨勢(shì)，說(shuō)明運(yùn)用線性Granger因果檢驗(yàn)得出的結(jié)論不準(zhǔn)確。因此，本文利用VAR模型先過濾掉HE和EFF兩者之間的線性關(guān)系，然后運(yùn)用非線性Granger因果關(guān)系檢驗(yàn)方法檢驗(yàn)兩者關(guān)系。結(jié)果表明，HE和EFF之間存在雙向的非線性Granger因果關(guān)系，這表明：深圳股票市場(chǎng)羊群效應(yīng)的強(qiáng)弱影響市場(chǎng)效率的高低，反過來(lái)，市場(chǎng)效率的高低也會(huì)影響羊群效應(yīng)的強(qiáng)弱。
[Abstract]:The irrational behavior of investors in stock market is one of the important objects of behavioral finance. The irrational behavior of investors not only increases the volatility of stock market, but also affects the efficiency of stock market. Methods based on the research, the new method of herding behavior test is discussed, and the relationship between herding behavior and market efficiency is further studied on the basis of herding behavior test in stock market. The main contents are as follows:. The first is the improvement of herding effect test method in stock market and the test of herding behavior in Shenzhen stock market. 1) on the basis of synthesizing the advantages of CCK I-CCK and T-CCK model, considering the heteroscedasticity effect of market, an improved herding effect test model-V-CCK model is put forward. 2) using the improved V-CCK model, the herding effect of Shenzhen stock market is tested and compared with the existing model. The results show that the proposed V-CCK model is better; (3) the static results show that, whether the stock market is rising or falling, there is a remarkable herding effect in Shenzhen stock market, but the herding effect is stronger when the stock market falls than that in the rising stock market, and the dynamic results show that, as time goes on, the herding effect in Shenzhen stock market is stronger than that in the rising stock market. The herding effect in the stock market tends to be weaker, and the herd effect is always stronger when the stock market falls than when the stock market is rising. Second, the relationship between herding effect and market efficiency in Shenzhen stock market. Using V-CCK model and MF-DMA (multifractal moving average elimination trend) method, the herding effect index (HE) and the validity index (EFF) are proposed, respectively. Using sliding window technique, the herding effect index sequence HEt and the validity index sequence EEFtare calculated respectively. Correlation test showed that there was a significant positive correlation between HE and EFF. (2) the results of linear Granger causality test showed that HE was not the linear Granger cause of EFF, but EFF was the linear Granger cause of HE. 3) the nonlinear test shows that there is an obvious trend of nonlinear dynamic change between HE and EFF variables, which indicates that the conclusion obtained by using linear Granger causality test is not accurate. In this paper, VAR model is used to filter out the linear relationship between HE and EFF, and then the nonlinear Granger causality test method is used to test the relationship. The results show that there is a bidirectional nonlinear Granger causality between HE and EFF. This indicates that the herding effect in Shenzhen stock market affects the market efficiency, and in turn, the market efficiency will also affect the herding effect.
【學(xué)位授予單位】：南京財(cái)經(jīng)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：F830.91;F224

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 阮青松;呂大永;;滬深300指數(shù)羊群效應(yīng)研究[J];商業(yè)研究;2010年08期

2 徐益華,楊曉明;中國(guó)證券市場(chǎng)效率的實(shí)證研究[J];財(cái)經(jīng)問題研究;2002年01期

3 葉中行,曹奕劍;Hurst指數(shù)在股票市場(chǎng)有效性分析中的應(yīng)用[J];系統(tǒng)工程;2001年03期

4 俞喬;市場(chǎng)有效、周期異常與股價(jià)波動(dòng)——對(duì)上海、深圳股票市場(chǎng)的實(shí)證分析[J];經(jīng)濟(jì)研究;1994年09期

5 宋軍,吳沖鋒;基于分散度的金融市場(chǎng)的羊群行為研究[J];經(jīng)濟(jì)研究;2001年11期

6 汪煒,周宇;中國(guó)股市“規(guī)模效應(yīng)”和“時(shí)間效應(yīng)”的實(shí)證分析——以上海股票市場(chǎng)為例[J];經(jīng)濟(jì)研究;2002年10期

7 賈麗杰;趙國(guó)杰;;中國(guó)股票市場(chǎng)羊群效應(yīng)檢驗(yàn)方法的改進(jìn)[J];統(tǒng)計(jì)與決策;2008年16期

8 樊智,張世英;金融市場(chǎng)的效率與分形市場(chǎng)理論[J];系統(tǒng)工程理論與實(shí)踐;2002年03期

9 劉波,曾勇,唐小我;中國(guó)股票市場(chǎng)羊群效應(yīng)的實(shí)證研究[J];運(yùn)籌與管理;2004年01期

10 李洪濤,譚智平,方兆本;深滬股市與香港股市的羊群效應(yīng)之比較[J];預(yù)測(cè);2002年06期

相關(guān)碩士學(xué)位論文 前1條

1 馮東方;中國(guó)股票市場(chǎng)多重分形特征及羊群行為關(guān)系研究[D];南京財(cái)經(jīng)大學(xué);2010年

本文編號(hào)：1683944