Robust Estimation of the Parameters of g - and - h Distributions, with Applications to Outlier Detection.

Robust Estimation of the Parameters of g - and - h Distributions, with Applications to Outlier Detection.
复制标题

DOI:
10.1016/j.csda.2014.01.003
复制
发表时间:
2014-07-01
影响因子:
1.8
通讯作者:
Chervoneva, Inna
Chervoneva, Inna
中科院分区:
数学3区
文献类型:
--
作者:
Xu, Yihuan;Iglewicz, Boris;Chervoneva, Inna

文献摘要

参考文献

被引文献

相似文献

g -和- h分布族是从标准正态分布的一个相对简单的变换中产生的,并且可以近似于广泛的分布谱。因此,它易于在模拟研究中使用,并已被应用于多个领域,包括风险管理,股票收益分析和缺失数据填补研究。本文提出了一种快速收敛的分位数最小二乘(QLS)估计方法来拟合g -和h-分布族参数,并将其推广到一个鲁棒的版本。鲁棒的版本,然后用作一个更一般的离群值检测方法。通过仿真,导出了QLS方法的一些性质,并与竞争方法进行了比较。真实的数据的例子,微阵列和股票指数数据被用来作为说明。
The g - and - h distributional family is generated from a relatively simple transformation of the standard normal and can approximate a broad spectrum of distributions. Consequently, it is easy to use in simulation studies and has been applied in multiple areas, including risk management, stock return analysis and missing data imputation studies. A rapidly convergent quantile based least squares (QLS) estimation method to fit the g - and - h distributional family parameters is proposed and then extended to a robust version. The robust version is then used as a more general outlier detection approach. Several properties of the QLS method are derived and comparisons made with competing methods through simulation. Real data examples of microarray and stock index data are used as illustrations.
DOI: 10.2307/2289073
发表时间: 1986-12-01
影响因子: 3.7
作者:
HOAGLIN, DC;IGLEWICZ, B;TUKEY, JW
通讯作者: TUKEY, JW
DOI: 10.1111/j.1369-7412.2003.05341.x
发表时间: 2004-01-01
影响因子: 5.8
作者:
Heggland, K;Frigessi, A
通讯作者: Frigessi, A
DOI: 10.1101/gr.10.12.2022
发表时间: 2000-12-01
期刊: GENOME RESEARCH
影响因子: 7
作者:
Callow, MJ;Dudoit, S;Rubin, EM
通讯作者: Rubin, EM
DOI: 10.1198/016214503388619102
发表时间: 2003-03-01
影响因子: 3.7
作者:
Genton, MG;Ronchetti, E
通讯作者: Ronchetti, E
DOI: 10.1016/s0167-9473(03)00069-0
发表时间: 2003-10-28
影响因子: 1.8
作者:
Kafadar, K;Phang, T
通讯作者: Phang, T