Functional regression with repeated eigenvalues

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We explore the functional principal component method for estimating regression parameters in functional linear models. We demonstrate that the commonly made assumption concerning unique eigenvalues is unnecessary. Convergence rates are established allowing a variety of sample spaces and dependence structures.

Original languageEnglish (US)
Pages (from-to)62-70
Number of pages9
JournalStatistics and Probability Letters
Volume107
DOIs
StatePublished - Dec 1 2015

Fingerprint

Functional Linear Model
Sample space
Dependence Structure
Principal Components
Convergence Rate
Regression
Eigenvalue
Demonstrate
Dependence structure
Eigenvalues
Principal components
Convergence rate

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{6a7e4b9c359f4d279209046bc234c547,
title = "Functional regression with repeated eigenvalues",
abstract = "We explore the functional principal component method for estimating regression parameters in functional linear models. We demonstrate that the commonly made assumption concerning unique eigenvalues is unnecessary. Convergence rates are established allowing a variety of sample spaces and dependence structures.",
author = "Reimherr, {Matthew Logan}",
year = "2015",
month = "12",
day = "1",
doi = "10.1016/j.spl.2015.07.037",
language = "English (US)",
volume = "107",
pages = "62--70",
journal = "Statistics and Probability Letters",
issn = "0167-7152",
publisher = "Elsevier",

}

Functional regression with repeated eigenvalues. / Reimherr, Matthew Logan.

In: Statistics and Probability Letters, Vol. 107, 01.12.2015, p. 62-70.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Functional regression with repeated eigenvalues

AU - Reimherr, Matthew Logan

PY - 2015/12/1

Y1 - 2015/12/1

N2 - We explore the functional principal component method for estimating regression parameters in functional linear models. We demonstrate that the commonly made assumption concerning unique eigenvalues is unnecessary. Convergence rates are established allowing a variety of sample spaces and dependence structures.

AB - We explore the functional principal component method for estimating regression parameters in functional linear models. We demonstrate that the commonly made assumption concerning unique eigenvalues is unnecessary. Convergence rates are established allowing a variety of sample spaces and dependence structures.

UR - http://www.scopus.com/inward/record.url?scp=84939799770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939799770&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2015.07.037

DO - 10.1016/j.spl.2015.07.037

M3 - Article

AN - SCOPUS:84939799770

VL - 107

SP - 62

EP - 70

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

SN - 0167-7152

ER -