Robust backfitting estimators for additive models

BOENTE, GRACIELA; MARTÍNEZ, ALEJANDRA; SALIBIAN-BARRERA, MATÍAS

Calcuta

Conferencia; International Conference on Robust Statistics (ICORS 2015); 2015

Indian Statistical Institute

We propose a robust backfitting estimator for additive models. The estimators are Fisher consistent under standard regularity assumptions and the algorithm is well-behaved. Through numerical experiments we will show that the robust estimator based on backfitting performs better than the one based on marginal integration.