The choice of the initial estimate for computing MM-estimates

We show, using a Monte Carlo study, that MM-estimates with projection estimates as starting point of an iterative weighted least squares algorithm, behave more robustly than MM-estimates starting at an S-estimate and similar Gaussian efficiency. Moreover the former have a robustness behavior close t...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Svarc, M., Yohai, V.J., et al.; Fundacao para a Ciencia e a Tecnologia (FCT); Instituto Nacional de Estatistica; PORTO Camara Municipal; PSE; Universidade do Porto - Faculdade de Engenharia (FEUP)
Formato: CONF
Materias:
P-estimates
Robust regression
S-estimates
Gaussians
Initial estimate
Iterative-weighted
Robust regressions
Statistical inference
Iterative methods
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_97837908_v_n_p503_Svarc
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires

Ejemplares similares

Ejemplares similares