Estimation of Stable Distributions by Indirect Inference
Estimation of Stable Distributions by Indirect Inference
复制标题
通过间接推理估计稳定分布
DOI：
10.2139/ssrn.795366
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
David Veredas
中科院分区：
文献类型：
--
作者：
René Garcia;É. Renault;David Veredas
本文以偏斜t分布为辅助模型，通过间接推理方法估计稳定分布的参数。后一种分布似乎是辅助模型的良好候选者，因为它具有与稳定分布相同数量的参数，并且每个参数都扮演着类似的角色。为了改进有限样本中估计器的性能，我们使用称为约束间接推理的方法的变体。在蒙特卡罗研究中，我们表明该方法在有限样本中提供了具有良好特性的估计量。特别是，它们比其他两种基于特征函数和经验分位数的流行方法要高效得多。我们提供对冲基金回报的实证应用。
This article deals with the estimation of the parameters of an -stable distribution by the indirect inference method with the skewed-t distribution as an auxiliary model. The latter distribution appears as a good candidate for an auxiliary model since it has the same number of parameters as the -stable distribution, with each parameter playing a similar role. To improve the properties of the estimator in finite sample, we use a variant of the method called Constrained Indirect Inference. In a Monte Carlo study, we show that this method delivers estimators with good properties in finite sample. In particular they are much more efficient than two other prevalent methods based on the characteristic function and the empirical quantiles. We provide an empirical application to hedge fund returns.