Multivariate skew-normal/independent distributions: properties and inference
Liu (1996) discussed a class of robust normal/independent distributions which contains a group of thick-tailed cases. In this article, we develop a skewed version of these distributions in the multivariate setting, and we call them multivariate skew normal/independent distributions. We derive severa...
Main Authors: | , |
---|---|
Format: | Others |
Language: | Español |
Published: |
Pontificia Universidad Católica del Perú
2014
|
Subjects: | |
Online Access: | http://revistas.pucp.edu.pe/index.php/promathematica/article/view/11234/11746 http://repositorio.pucp.edu.pe/index/handle/123456789/97108 |
id |
ndltd-PUCP-oai-tesis.pucp.edu.pe-123456789-97108 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-PUCP-oai-tesis.pucp.edu.pe-123456789-971082018-08-07T16:41:41Z Multivariate skew-normal/independent distributions: properties and inference Multivariate skew-normal/independent distributions: properties and inference Lachos, Victor H. Labra, Filidor V. Em Algorithm Normal/Independent Distributions Skewness Measurement Errors Models 62f03 62f05 62f10 62f12 Algoritmo Em Normal/Independiente 62f03 62f05 62f10 62f12 Liu (1996) discussed a class of robust normal/independent distributions which contains a group of thick-tailed cases. In this article, we develop a skewed version of these distributions in the multivariate setting, and we call them multivariate skew normal/independent distributions. We derive several useful properties for them. The main virtue of the members of this family is that they are easy to simulate and lend themselves to an EM-type algorithm for maximum likelihood estimation. For two multivariate models of practical interest, the EM-type algorithm has been discussed with emphasis on the skew-t, the skew-slash, and the contaminated skew-normal distributions. Results obtained from simulated and two real data sets are also reported. Liu (1996) discute una clase de distribuciones robustas a las que apela como normal/independiente, y que contiene un grupo de distribuciones de colas pesadas. En este artículo desarrollamos una versión asimétrica de tales distribuciones en un escenario multivariado, a las que llamaremos distruciones normales asimétricas independientes multivariadas. Para tales distribuciones derivamos algunas propiedades. La principal virtud de los miembros de esta familia es que son fáciles de simular y se prestan a un algoritmo de tipo EM para realizar estimaciones de máxima verosimilitud de sus parámetros. Para dos modelos multivariados de interés práctico se discute el algoritmo EM con énfasis en las distribuciones t-asimétrica, slash asimétrica y normal asimétrica contaminada. Los resultados obtenidos a partir de simulaciones y de dos conjuntos de datos reales son reportados. 2014-12-17 2017-09-25T21:47:09Z 2017-09-25T21:47:09Z Artículo http://revistas.pucp.edu.pe/index.php/promathematica/article/view/11234/11746 http://repositorio.pucp.edu.pe/index/handle/123456789/97108 Español Artículo en acceso abierto Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/ PDF Pontificia Universidad Católica del Perú Pro Mathematica; Vol. 28, Núm. 56 (2014); 11-53 |
collection |
NDLTD |
language |
Español |
format |
Others
|
sources |
NDLTD |
topic |
Em Algorithm Normal/Independent Distributions Skewness Measurement Errors Models 62f03 62f05 62f10 62f12 Algoritmo Em Normal/Independiente 62f03 62f05 62f10 62f12 |
spellingShingle |
Em Algorithm Normal/Independent Distributions Skewness Measurement Errors Models 62f03 62f05 62f10 62f12 Algoritmo Em Normal/Independiente 62f03 62f05 62f10 62f12 Lachos, Victor H. Labra, Filidor V. Multivariate skew-normal/independent distributions: properties and inference |
description |
Liu (1996) discussed a class of robust normal/independent distributions which contains a group of thick-tailed cases. In this article, we develop a skewed version of these distributions in the multivariate setting, and we call them multivariate skew normal/independent distributions. We derive several useful properties for them. The main virtue of the members of this family is that they are easy to simulate and lend themselves to an EM-type algorithm for maximum likelihood estimation. For two multivariate models of practical interest, the EM-type algorithm has been discussed with emphasis on the skew-t, the skew-slash, and the contaminated skew-normal distributions. Results obtained from simulated and two real data sets are also reported. === Liu (1996) discute una clase de distribuciones robustas a las que apela como normal/independiente, y que contiene un grupo de distribuciones de colas pesadas. En este artículo desarrollamos una versión asimétrica de tales distribuciones en un escenario multivariado, a las que llamaremos distruciones normales asimétricas independientes multivariadas. Para tales distribuciones derivamos algunas propiedades. La principal virtud de los miembros de esta familia es que son fáciles de simular y se prestan a un algoritmo de tipo EM para realizar estimaciones de máxima verosimilitud de sus parámetros. Para dos modelos multivariados de interés práctico se discute el algoritmo EM con énfasis en las distribuciones t-asimétrica, slash asimétrica y normal asimétrica contaminada. Los resultados obtenidos a partir de simulaciones y de dos conjuntos de datos reales son reportados. |
author |
Lachos, Victor H. Labra, Filidor V. |
author_facet |
Lachos, Victor H. Labra, Filidor V. |
author_sort |
Lachos, Victor H. |
title |
Multivariate skew-normal/independent distributions: properties and inference |
title_short |
Multivariate skew-normal/independent distributions: properties and inference |
title_full |
Multivariate skew-normal/independent distributions: properties and inference |
title_fullStr |
Multivariate skew-normal/independent distributions: properties and inference |
title_full_unstemmed |
Multivariate skew-normal/independent distributions: properties and inference |
title_sort |
multivariate skew-normal/independent distributions: properties and inference |
publisher |
Pontificia Universidad Católica del Perú |
publishDate |
2014 |
url |
http://revistas.pucp.edu.pe/index.php/promathematica/article/view/11234/11746 http://repositorio.pucp.edu.pe/index/handle/123456789/97108 |
work_keys_str_mv |
AT lachosvictorh multivariateskewnormalindependentdistributionspropertiesandinference AT labrafilidorv multivariateskewnormalindependentdistributionspropertiesandinference |
_version_ |
1718721192714567680 |