A fast method for implementing Generalized Cross-Validation in multi-dimensional nonparametric regression

Kauermann, Göran and Opsomer, J. D. (2001): A fast method for implementing Generalized Cross-Validation in multi-dimensional nonparametric regression. Collaborative Research Center 386, Discussion Paper 247

Abstract

This article presents a modified Newton method for minimizing the Generalized Cross-Validation criterion, a commonly used smoothing parameter selection method in nonparametric regression. The method is applicable to higher dimensional problems such as additive and generalized additive models, and provides a computationally efficient alternative to full grid search in such cases. The implementation of the proposed method requires the estimation of a number of auxiliary quantities, and simple estimators are suggested. This article describes the methodology for local polynomial regression smoothing.

• Item Type: Paper
• Keywords: local polynomial regression, generalized additive model, Newton method
• Faculties: Mathematics, Computer Science and Statistics > Statistics > Collaborative Research Center 386; Special Research Fields > Special Research Field 386
• Subjects: 500 Science > 510 Mathematics
• Language: English