摘要
对股票交易中的大单交易行为所展示的群体水平上的人类动力学做了实证分析。统计数据显示:股票大单交易时间间隔服从幂律分布,其分布图在双对数坐标下具有明显的胖尾特性;有些股票的时间间隔分布出现了断尾特性,拟合后的幂指数的数值分布区间跨度相对较大。在相同的时间段内,股票的活跃程度与大单交易次数呈现正相关关系,活跃程度与拟合后的幂指数的原始数据没有明显的正相关关系,但是对幂指数进行奇数次移动平均后,活跃程度与幂指数呈现明显的正相关关系。
Empirical analysis of the human dynamics in the group level of big deal in the stock trading is studied in this paper. Statistics data show that time interval of big deal obeys the power-law distribution with obvious heavy-tailed character on the double logarithm coordinates. Broken-tailed is found in the time interval distribu- tion of some stocks. The fitted power-exponential value interval span is relatively large. At the same time, the relationship of positive correlation is found between the activity and the number of big deal. There is no signifi- cant positive correlation between activity and the raw data of the fitted exponent. But after moving and averaging the power exponent odd times, the activity and power exponent is obviously positive.
出处
《桂林理工大学学报》
CAS
北大核心
2012年第1期149-153,共5页
Journal of Guilin University of Technology
基金
国家自然科学基金项目(61164020
61004101)
广西自然科学基金项目(2011GXNSFA018147)
广西空间信息与测绘重点实验室项目(桂科能1103108-24)
关键词
人类动力学
股票
大单交易
幂律分布
human dynamics
stock
big deal
power-law distribution