股指期货操纵预警的Logistic模型实证研究  被引量:11

Empirical study on early warning of stock index futures manipulation based on logistic model

在线阅读下载全文

作  者:熊熊[1] 张宇 张维[1] 张永杰[1] 

机构地区:[1]天津大学管理与经济学部,天津300072 [2]银行业监督管理委员会山东监管局,济南250001

出  处:《系统工程理论与实践》2011年第7期1287-1292,共6页Systems Engineering-Theory & Practice

基  金:教育部新世纪优秀人才支持计划项目(NCET-07-0605);国家自然科学基金(70971096;70801043);中国期货行业协会联合研究计划(GT200702);天津社会科学基金(TJ05-TJ003)

摘  要:通过建立Logistic回归模型判别股指期货被操纵的可能性,将股指期货是否被操纵的问题转化为根据一定时期内股指期货市场的波动性以及流动性指标计算股指期货在一定时间内被操纵的概率,建立了股指期货操纵事件的预警模型.选取香港恒生指数期货操纵时段和对应的非操纵时段,进行了预警模型的实证检验,证明了该模型可以对股指期货操纵事件起到较好的预警作用.研究发现,在股指期货市场中,操纵期与非操纵期的交易量和空盘量显著不同,而反映市场波动性的收益率指标的变化并不显著,对操纵行为是否发生可以使用空盘量和交易量构建模型进行判别.Logistic模型可以很好的识别股指期货市场上的操纵行为,在进入操纵期以后,根据模型计算出的操纵事件的发生概率发生了显著的变化.Most studies on early warning of the security or futures market. With the rapid development of Stock market manipulation only focus on stock market Index Futures, the early warning of Stock Index Futures manipulation becomes very important. This paper, based on Logistic Regression Model, uses the volatility and liquidity indicators to estimate the probability of Stock Index Futures Market manipulation and sets up a early warning model on Stock Index Futures Market manipulation. Further, the inter-day transaction data of Hang Seng Index Futures both during the period of manipulation and the period of non-manipulation are used to test our model. The empirical results show that this model can give good early warning on Stock Index Futures Market manipulation events. We also find that the trading volume and Open-int are significantly different between the manipulation period and non-manipulation period, but the changes of volatility and yield ratio aren't so significant. So we can use the trading volume and Openint to distinguish the manipulation events. According to our empirical study, we find, during manipulation periods, there are significant changes in the probability of Stock Index Futures Market manipulation. Our Logistic model can identify the manipulation in Stock Index Futures market effectively.

关 键 词:股指期货 预警 LOGISTIC回归 操纵 

分 类 号:F830.91[经济管理—金融学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象