Influence diagnostics in exponentiated-Weibull regression models with censored data.

Título inglés	Influence diagnostics in exponentiated-Weibull regression models with censored data.
Título español	Diagnóstico de influencia en modelos de regresión exponencial-Weibull con datos censurados.
Autor/es	Ortega, Edwin M. M. ; Cancho, Vicente G. ; Bolfarine, Heleno
Organización	ESALQ. Univ. Sâo Paulo, Sâo Paulo, Brasil;ICM. Univ. Sâo Paulo, Sâo Paulo, Brasil;IME. Univ. Sâo Paulo, Sâo Paulo, Brasil
Revista	1696-2281
Publicación	2006, 30 (2): 171-192, 40 Ref.
Tipo de documento	articulo
Idioma	Inglés
Resumen inglés	Diagnostic methods have been an important tool in regression analysis to detect anomalies, such as departures from the error assumptions and the presence of outliers and influential observations with the fitted models. The literature provides plenty of approaches for detecting outlying or influential observations in data sets. In this paper, we follow the local influence approach (Cook 1986) in detecting influential observations with exponentiated-Weibull regression models. The relevance of the approach is illustrated with a real data set, where it is shown that by removing the most influential observations, there is a change in the decision about which model fits the data better.
Clasificación UNESCO	120913
Palabras clave español	Análisis de regresión ; Análisis de datos censurados ; Distribución exponencial ; Distribución de Weibull
Código MathReviews	MR2300558
Acceso al artículo completo