English

Bootstrap independence test for functional linear models

Methodology 2020-09-22 v4

Abstract

Functional data have been the subject of many research works over the last years. Functional regression is one of the most discussed issues. Specifically, significant advances have been made for functional linear regression models with scalar response. Let (H,<,>)(\mathcal{H},<\cdot,\cdot>) be a separable Hilbert space. We focus on the model Y=<Θ,X>+b+εY=<\Theta,X>+b+\varepsilon, where YY and ε\varepsilon are real random variables, XX is an H\mathcal{H}-valued random element, and the model parameters bb and Θ\Theta are in R\mathbb{R} and H\mathcal{H}, respectively. Furthermore, the error satisfies that E(εX)=0E(\varepsilon|X)=0 and E(ε2X)=σ2<E(\varepsilon^2|X)=\sigma^2<\infty. A consistent bootstrap method to calibrate the distribution of statistics for testing H0:Θ=0H_0: \Theta=0 versus H1:Θ0H_1: \Theta\neq 0 is developed. The asymptotic theory, as well as a simulation study and a real data application illustrating the usefulness of our proposed bootstrap in practice, is presented.

Keywords

Cite

@article{arxiv.1210.1072,
  title  = {Bootstrap independence test for functional linear models},
  author = {Wenceslao González-Manteiga and Gil González-Rodríguez and Adela Martínez-Calvo and Eduardo García-Portugués},
  journal= {arXiv preprint arXiv:1210.1072},
  year   = {2020}
}

Comments

17 pages, 5 tables

R2 v1 2026-06-21T22:15:20.319Z