Robust mixture regression based on the skew t distribution
In this study, we propose a robust mixture regression procedure based on the skew t distribution to model heavy-tailed and/or skewed errors in a mixture regression setting. Using the scale mixture representation of the skew t distribution, we give an Expectation Maximization (EM) algorithm to compu...
- Autores:
-
Doğru, Fatma Zehra
Arslan, Olcay
- Tipo de recurso:
- Article of journal
- Fecha de publicación:
- 2017
- Institución:
- Universidad Nacional de Colombia
- Repositorio:
- Universidad Nacional de Colombia
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.unal.edu.co:unal/66504
- Acceso en línea:
- https://repositorio.unal.edu.co/handle/unal/66504
http://bdigital.unal.edu.co/67532/
- Palabra clave:
- 51 Matemáticas / Mathematics
31 Colecciones de estadística general / Statistics
Mixture regression models
robust regression
maximum likelihood
EM algorithm
skew t distribution
Algoritmo EM
máxima verosimilitud
mixtura de regresiones
distribución t asimétrica.
- Rights
- openAccess
- License
- Atribución-NoComercial 4.0 Internacional
| Summary: | In this study, we propose a robust mixture regression procedure based on the skew t distribution to model heavy-tailed and/or skewed errors in a mixture regression setting. Using the scale mixture representation of the skew t distribution, we give an Expectation Maximization (EM) algorithm to compute the maximum likelihood (ML) estimates for the paramaters of interest. The performance of proposed estimators is demonstrated by a simulation study and a real data example. |
|---|