12,000

We have over 12,000 students, from over 100 countries, within one of the safest campuses in the UK

93%

93% of Lancaster students go into work or further study within six months of graduating

Home > Research > Publications & Outputs > Estimation of a functional single index model
View graph of relations

« Back

Estimation of a functional single index model

Research output: Contribution in Book/Report/ProceedingsPaper

Published

Publication date2011
Host publicationRecent Advances in Functional Data Analysis and Related Topics
EditorsFrédéric Ferraty
Place of publicationBerlin
PublisherPhysica-Verlag HD
Pages111-116
Number of pages6
ISBN (Electronic)978-3-7908-2736-1
ISBN (Print)978-3-7908-2735-4
Original languageEnglish

Abstract

Single index models have been mostly studied as an alternative dimension reduction technique for nonparametric regression with multivariate covariates. The index parameter appearing in the model summarizes the effect of the covariates in a finite dimensional vector. We consider an extension to a functional single index parameter which is of infinite dimensional, as a summary of the effect of a functional explanatory variable on a scalar response variable and propose a new estimator based on the idea of functional derivative estimation.