The backfitting and marginal integration estimators for additive models
- Zofia Łabęda-Grudziak
This article describes statistical methods that may be used to identify and characterize nonlinear regression effects. These methods are called additive models. The additive models are attractive as they provide effective dimension and great flexibility in modeling. In particular, the methods for estimating the additive functions have been presented, including the backfitting algorithm and the Linton-Nielsen method. The backfitting algorithm is an iterative procedurę in which, at each step, one component is estimated keeping the other components fixed, the algorithm proceeding component by component and iterating until convergence. The LintonNielsen algorithm is non-iterative procedure and is based on marginal integration. A simulationstudy comparing methods is presented. Obtained results show, that the backfitting estimators are widely use in nonlinear case and marginal integration estimators produce the fits that closely match the linear relationship between a dependent and univariate independent variable.
- Record ID
- Publication size in sheets
- IV Międzynarodowa Konferencja Naukowo-Techniczna Doktorantów i Młodych Naukowców – materiały konferencyjne, 2009, Oficyna Wydawnicza Politechniki Warszawskiej
- Keywords in English
- additive model, backfitting estimator, marginal integration estimator, model selection, nonparametric regression
- (en) English
- Score (nominal)
- Uniform Resource Identifier
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or PerishOpening in a new tab system.