Premium
Variable selection in generalized functional linear models
Author(s) -
Gertheiss Jan,
Maity Arnab,
Staicu AnaMaria
Publication year - 2013
Publication title -
stat
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.61
H-Index - 18
ISSN - 2049-1573
DOI - 10.1002/sta4.20
Subject(s) - selection (genetic algorithm) , variable (mathematics) , feature selection , linear model , generalized linear model , mathematics , computer science , statistics , artificial intelligence , mathematical analysis
Modern research data, where a large number of functional predictors is collected on few subjects are becoming increasingly common. In this paper we propose a variable selection technique, when the predictors are functional and the response is scalar. Our approach is based on adopting a generalized functional linear model framework and using a penalized likelihood method that simultaneously controls the sparsity of the model and the smoothness of the corresponding coefficient functions by adequate penalization. The methodology is characterized by high predictive accuracy, and yields interpretable models, while retaining computational efficiency. The proposed method is investigated numerically in finite samples, and applied to a diffusion tensor imaging tractography data set and a chemometric data set. Copyright © 2013 John Wiley & Sons Ltd