基于StN分布联合位置,尺度与偏度模型的极大似然估计

Maximum likelihood estimation for joint location,scale and skewness models of the StN distribution

在社会,经济领域中异方差数据的大量存在表明方差建模与均值建模同等重要,而相对于对称分布,有偏分布更能获得准确有效的信息,对偏度建模,了解影响偏度的因素具有理论与实际意义.基于以上两点,文中提出了于Skew-t-Normal(StN)偏态分布的联合位置,尺度与偏度模型,并研究了该模型参数的极大似然估计,模拟和实例研究结果表明该模型和方法是有用和有效的.

In the social and economic fields, there are a large number of heteroscedastic data. This shows modeling of the variance can be as important as that of the mean. Compared with the symmetric distribution, skew-normal distribution can obtain more comprehensive, more accurate and effective information. To understand the effects of skewness, skewness modeling has both theoretical and practical significance. Based on the above two points, the maximum likelihood estimation for joint location, scale and skewness models of the Skew-t-Normal（StN） distribution is proposed. Simulation studies and a real example show that these results and methods are useful and effective.