Approximation by normal distribution with covering width based EM estimation
-
摘要: 提出了非正态分布的有限混合正态分布的逼近思路.为了解决混合正态分布中正态分布个数的确定问题,针对基于极大似然估计的期望最大化(EM,Expectation Maximization)算法,提出了最大覆盖宽度的定阶原则.实证结果表明该方法的可行性.在阶数确定上,最大覆盖准则要优于赤池信息准则,而在宽度计算中,对于最大均值和最小均值的基于标准差的权重调整是必要的.Abstract: Based on the comparison and analysis on existingnon-normal distributions, the approximation method by using mixture normal distributions was proposed. For overcoming the order determination difficultyin maximum likelihood estimation based expectation maximization (EM) algorithm, the maximalcovering width principle (MCWP) for order determining was designed. The experiment result supports the feasibility of the method. It shows that the fitting by MCWP has the advantage of the Akaike information criterion. In calculating the covering width, it is necessary to adjust the maximum mean and the minimum mean by the standard deviationbased weights.
-
[1] Kim Y S,Rachev S T,Bianchi M L,et al.Financial market models with levy process and time-varying volatility[J].Journal of Banking & Finance,2008,32(7):1363-1378 [2] Longin F.The asymptotic distribution of extreme stock market returns[J].Journal of Business,1996,69(7):383-408 [3] Nolan J P.Stabledistributions:models for heavy-tailed data[M].Verlag:Birkhauser,2003 [4] Mantegna R N,Buldyrev S V,Goldberger A L,et al.Linguistic features of noncoding DNA sequences[J].Physical Review Letters,1994,73(23):3169-3172 [5] Koponen Ismo.Analytic approach to the problem of convergence of truncated Lévy flights towards the Gaussian stochastic process[J].Phys Rev E,1995,52:1197-1199 [6] Gupta H M,CampanhaJ R.The gradually truncated Lévy flight for systems with power-law distributions[J].Physica A:Statistical Mechanics and Its Applications,1999,268(1):231-239 [7] Matsushita R,Rathie P,Silva S D.Exponentially damped Lévy flights[J].Physica A:Statistical Mechanics and Its Applications,2003,326(3):544-555 [8] Gleria I,Figueiredo A,Matsushita R,et al.Exponentially damped Lévy flights,multiscaling and slow convergence in stock markets[J].Physica A:Statistical Mechanics and Its Applications,2004,342(1):200-206 [9] 陈启欢.中国股票市场收益率分布曲线的实证[J].数理统计与管理,2002,21(5):9-11
Chen Qihuan.The curve of stock market yield in China[J].Journal of Application of Statistics and Management,2002, 21(5): 9-11 (in Chinese)[10] 王新宇,宋学峰.拟合中国股票市场收益的统计分布[J].系统工程理论与实践,2006(12):40-46
Wang Xinyu,Song Xuefeng.A study on describing the statistical distribution of returns in Chinese stock markets[J].Systems Engineering-Theory & Practice,2006(12):40-46(in Chinese)[11] 都国雄,宁宣熙.我国股市收益概率分布的统计特性分析[J].中国管理科学,2007,15(5):16-22
Du Guoxiong,Ning Xuanxi.Statistical properties of probability distributions of returns in Chinese stock markets[J].Chinese Journal of Management Science,15(5):16-22(in Chinese)[12] 黄德龙,杨晓光.中国证券市场股指收益分布的实证分析[J].管理科学学报,2008,11(1):68-77
Huang Delong,Yang Xiaoguang.Empirical study on distributions of stock index returns in China's securities market[J].Journal of Management Sciences in China,2008,11(1):68-77 (in Chinese)[13] James S.A compound events model for security prices[J].The Journal of Business,1967,40(3):317-335 [14] Praetz P.The distribution of share price changes[J].Journal of Business,1972,45(1):49-55 [15] Blattberg,R C,Nicholas J G.A comparison of the stable and student distributions as statistical models for stock prices[J].Journal of Business,1974,47(2):244-280 [16] 赵希男,崔海波.确定金融资产收益率分布形式的一种方法[J].数量经济技术经济研究,2004(9):56-63
Zhao Xi-nan,Cui Haibo.A kind of methods to determining return distributions of financial assets[J].Quantitative & Technical Economics,2004(9):56-63(in Chinese)[17] Dempster,Nan Laird,Donald Rubin.Maximum likelihood from incomplete data via the EM algorithm[J].Journal of the Royal Statistical Society:Series B,1977,39(1):1-38 [18] 熊明,谢民育.均值混合正态分布统计量的性质[J].数学物理学报,2009(3):685-690
Xiong Ming,Xie Minyu.The properties of the mean-mixture of normal distribution[J].Acta Mathematica Scientia,2009(3):685-690(in Chinese)[19] Caudill S B.A partially adaptive estimator for the censored regression model based on a mixture of normal distributions[J].Statistical Methods and Applications,2012,21:121-137
点击查看大图
计量
- 文章访问数: 1469
- HTML全文浏览量: 128
- PDF下载量: 740
- 被引次数: 0