A股价格波动真的非平稳?——大数据背景下个股数据的全样本实证
|
摘要
传统研究对股票市场平稳性分析中大多采用市场指数抽样方式,分析方法和数据采样的差异一定程度上解析了现有研究结论中的不一致性。从市场指数构建原理入手可探究抽样分析的局限,作为系列个股的加权值,市场指数无法精确刻画市场所有个股的波动情况。实证时采用A股市场所有个股数据开展全样本分析,这更符合大数据分析理念,统计出个股分析结果继而对A股市场波动进行判定将更加系统和可靠。在不考虑结构突变的情形下,分别计算出ADF检验、KPSS检验和PP检验三种方法的结果;全样本分析结果表明A股市场年度股价数据更多地呈现出平稳性特点,而且,个股数据检验结果与市场指数检验结果存在显著差异。
The traditional research on the stock market stability analysis mostly uses sampling mode of the market index,so the differences between analysis method and data sampling to some extent give an explanation to the inconsistency of existing research conclusions. Starting with the principle of market index construction,the paper analyzes the limitation of sampling method. As a weighted value of a series of individual stocks,market index may not accurately depict the fluctuation of all individual stocks in the market.In order to be more in line with big data's analysis concept,the article uses all the A-share market data in China to carry out full-sample analysis,and work out all individual stock results which be more systematic and reliable to judge the fluctuation of A-share market. And then the results of ADF test,KPSS test and PP test were calculated without considering the structural mutation. The results of full-sample analysis show that the annual stock price data of A-share market present more stationary,moreover,the test results of individual stock data are significantly different from the market index's.
The traditional research on the stock market stability analysis mostly uses sampling mode of the market index,so the differences between analysis method and data sampling to some extent give an explanation to the inconsistency of existing research conclusions. Starting with the principle of market index construction,the paper analyzes the limitation of sampling method. As a weighted value of a series of individual stocks,market index may not accurately depict the fluctuation of all individual stocks in the market.In order to be more in line with big data's analysis concept,the article uses all the A-share market data in China to carry out full-sample analysis,and work out all individual stock results which be more systematic and reliable to judge the fluctuation of A-share market. And then the results of ADF test,KPSS test and PP test were calculated without considering the structural mutation. The results of full-sample analysis show that the annual stock price data of A-share market present more stationary,moreover,the test results of individual stock data are significantly different from the market index's.
引文
[1]李京.深沪A股指数单位根现象的实证研究[D].厦门:厦门大学硕士学位论文,2002.
[2]孙便霞,韩鹏,王明进.随机波动率模型下的单位根检验及对我国股市的实证研究[J].数理统计与管理,2008,27(1):148-155.
[3]刘田.非线性趋势单位根检验研究[D].成都:西南财经大学博士学位论文,2009.
[4]孙建明.股市价格指数成交量的单位根及因果关系检验[J].华中科技大学学报(自然科学版),2003(10):106-108.
[5]夏南新.单位根的DF、ADF检验与PP检验比较研究[J].数量经济技术经济研究,2005(9):130-136.
[6]李双琦.基于分形理论的上海证券市场有效性研究[D].重庆:重庆工商大学硕士学位论文,2016.
[7]王丽.上海股票市场有效性实证研究[J].时代金融,2017(26):195-196.
[8]张春丽,杨利雄,李庆男.傅里叶型平滑结构突变下Dickey-Fuller检验的功效---兼论Shibor的平稳性[J].统计与信息论坛,2016,31(5):21-26.
[9]佟孟华,钟春仿,郭多祚.结构突变及其对上证指数的实证研究[J].财经问题研究,2004(3):76-79.
[10]周宏山,路维春.中国股票指数的结构断点根检验研究[J].经济问题,2007(2):105-106.
[11]巴曙松,覃川桃,朱元倩.中国股票市场与房地产市场的联动关系[J].系统工程,2009,27(9):22-28.
[12]杨利雄,张春丽.基于傅里叶变换的含确定性趋势结构突变的协整回归模型和不等方差检验[J].统计研究,2014,3(11):96-100.
[13]韩青.中国宏观经济时序的平稳性再考察---内生突变与平滑转换[J].经济学(季刊),2015,14(2):801-826.
[14]侯春艳,李俊林,董安强.股票资金流强弱指数的结构突变研究[J].科技和产业,2017,17(2):168-172.
[15]纪思亮.数据圈宫心计:大数据与随机抽样---统计学必须进行技术革命[J].中国统计,2016(8):16-19.
[16]VIKTOR M S.Big data:a revolution that will transform how we live,work,and think[M].London:John Murray publisher,2013.
[17]Committee on the Analysis of Massive Data,et al.Frontiers in Massive Data Analysis[M].Washington:National A-cademies Press,2013.
[18]HARFORD T.Big data:A big mistake?[J].Significance,2015,11(5):14-19.
[19]朱建平,章贵军,刘晓葳.大数据时代下数据分析理念的辨析[J].统计研究,2014,31(2):10-19.
[20]耿直.大数据时代统计学面临的机遇与挑战[J].统计研究,2014,31(1):5-9.
[21]潘利明.简述抽样调查在“大数据”时代下的意义[J].现代经济信息,2016(1):103.
[22]程开明,宋艺旋.大数据还需要抽样吗[J].中国统计,2017(11):10-13.
[23]李子奈.高级应用计量经济学[M].北京:清华大学出版社,2012.
[2]孙便霞,韩鹏,王明进.随机波动率模型下的单位根检验及对我国股市的实证研究[J].数理统计与管理,2008,27(1):148-155.
[3]刘田.非线性趋势单位根检验研究[D].成都:西南财经大学博士学位论文,2009.
[4]孙建明.股市价格指数成交量的单位根及因果关系检验[J].华中科技大学学报(自然科学版),2003(10):106-108.
[5]夏南新.单位根的DF、ADF检验与PP检验比较研究[J].数量经济技术经济研究,2005(9):130-136.
[6]李双琦.基于分形理论的上海证券市场有效性研究[D].重庆:重庆工商大学硕士学位论文,2016.
[7]王丽.上海股票市场有效性实证研究[J].时代金融,2017(26):195-196.
[8]张春丽,杨利雄,李庆男.傅里叶型平滑结构突变下Dickey-Fuller检验的功效---兼论Shibor的平稳性[J].统计与信息论坛,2016,31(5):21-26.
[9]佟孟华,钟春仿,郭多祚.结构突变及其对上证指数的实证研究[J].财经问题研究,2004(3):76-79.
[10]周宏山,路维春.中国股票指数的结构断点根检验研究[J].经济问题,2007(2):105-106.
[11]巴曙松,覃川桃,朱元倩.中国股票市场与房地产市场的联动关系[J].系统工程,2009,27(9):22-28.
[12]杨利雄,张春丽.基于傅里叶变换的含确定性趋势结构突变的协整回归模型和不等方差检验[J].统计研究,2014,3(11):96-100.
[13]韩青.中国宏观经济时序的平稳性再考察---内生突变与平滑转换[J].经济学(季刊),2015,14(2):801-826.
[14]侯春艳,李俊林,董安强.股票资金流强弱指数的结构突变研究[J].科技和产业,2017,17(2):168-172.
[15]纪思亮.数据圈宫心计:大数据与随机抽样---统计学必须进行技术革命[J].中国统计,2016(8):16-19.
[16]VIKTOR M S.Big data:a revolution that will transform how we live,work,and think[M].London:John Murray publisher,2013.
[17]Committee on the Analysis of Massive Data,et al.Frontiers in Massive Data Analysis[M].Washington:National A-cademies Press,2013.
[18]HARFORD T.Big data:A big mistake?[J].Significance,2015,11(5):14-19.
[19]朱建平,章贵军,刘晓葳.大数据时代下数据分析理念的辨析[J].统计研究,2014,31(2):10-19.
[20]耿直.大数据时代统计学面临的机遇与挑战[J].统计研究,2014,31(1):5-9.
[21]潘利明.简述抽样调查在“大数据”时代下的意义[J].现代经济信息,2016(1):103.
[22]程开明,宋艺旋.大数据还需要抽样吗[J].中国统计,2017(11):10-13.
[23]李子奈.高级应用计量经济学[M].北京:清华大学出版社,2012.