INVESTIGADORES
BOENTE BOENTE Graciela Lina
congresos y reuniones científicas
Título:
Robust procedures in generalized partially linear models
Autor/es:
BOENTE, GRACIELA; RODRIGUEZ, DANIELA
Lugar:
Leuven
Reunión:
Workshop; International Workshop on Flexible Modelling, Smoothing and Robustness. (FMSR2008); 2008
Institución organizadora:
Katholieke Universiteit Leuven
Resumen:
In this talk, we will first discuss the sensitivity to outliers of the classical estimates for generalized partially linear models that is good evidence that robust methods are needed. The problem of obtaining a family of robust estimates was first considered by Boente, He and Zhou (2006). However, their procedure is computationally expensive. We will introduce a general three?step robust procedure to estimate the parameter and the function , under a generalized partly linear model, that is faster to compute than the one previously introduced. It will be shown that the estimates of are root-n consistent and asymptotically normal and we will present the results of a Monte Carlo study. A robust procedure to choose the smoothing parameter will also be described.
