Boosting local quasi-likelihood estimators

Masao Ueki, Kaoru Fueda

Research output: Contribution to journalArticle

Abstract

For likelihood-based regression contexts, including generalized linear models, this paper presents a boosting algorithm for local constant quasi-likelihood estimators. Its advantages are the following: (a) the one-boosted estimator reduces bias in local constant quasi-likelihood estimators without increasing the order of the variance, (b) the boosting algorithm requires only one-dimensional maximization at each boosting step and (c) the resulting estimators can be written explicitly and simply in some practical cases.

Original languageEnglish
Pages (from-to)235-248
Number of pages14
JournalAnnals of the Institute of Statistical Mathematics
Volume62
Issue number2
DOIs
Publication statusPublished - Apr 2010

Fingerprint

Quasi-likelihood
Boosting
Estimator
Generalized Linear Model
Likelihood
Regression

Keywords

  • Bias reduction
  • Generalized linear models
  • Kernel regression
  • L Boosting
  • Local quasi-likelihood
  • Nadaraya - Watson estimator

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

Boosting local quasi-likelihood estimators. / Ueki, Masao; Fueda, Kaoru.

In: Annals of the Institute of Statistical Mathematics, Vol. 62, No. 2, 04.2010, p. 235-248.

Research output: Contribution to journalArticle

Ueki, Masao ; Fueda, Kaoru. / Boosting local quasi-likelihood estimators. In: Annals of the Institute of Statistical Mathematics. 2010 ; Vol. 62, No. 2. pp. 235-248.
@article{685ea16563ef4bb682b97553d2ce5eed,
title = "Boosting local quasi-likelihood estimators",
abstract = "For likelihood-based regression contexts, including generalized linear models, this paper presents a boosting algorithm for local constant quasi-likelihood estimators. Its advantages are the following: (a) the one-boosted estimator reduces bias in local constant quasi-likelihood estimators without increasing the order of the variance, (b) the boosting algorithm requires only one-dimensional maximization at each boosting step and (c) the resulting estimators can be written explicitly and simply in some practical cases.",
keywords = "Bias reduction, Generalized linear models, Kernel regression, L Boosting, Local quasi-likelihood, Nadaraya - Watson estimator",
author = "Masao Ueki and Kaoru Fueda",
year = "2010",
month = "4",
doi = "10.1007/s10463-008-0173-5",
language = "English",
volume = "62",
pages = "235--248",
journal = "Annals of the Institute of Statistical Mathematics",
issn = "0020-3157",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Boosting local quasi-likelihood estimators

AU - Ueki, Masao

AU - Fueda, Kaoru

PY - 2010/4

Y1 - 2010/4

N2 - For likelihood-based regression contexts, including generalized linear models, this paper presents a boosting algorithm for local constant quasi-likelihood estimators. Its advantages are the following: (a) the one-boosted estimator reduces bias in local constant quasi-likelihood estimators without increasing the order of the variance, (b) the boosting algorithm requires only one-dimensional maximization at each boosting step and (c) the resulting estimators can be written explicitly and simply in some practical cases.

AB - For likelihood-based regression contexts, including generalized linear models, this paper presents a boosting algorithm for local constant quasi-likelihood estimators. Its advantages are the following: (a) the one-boosted estimator reduces bias in local constant quasi-likelihood estimators without increasing the order of the variance, (b) the boosting algorithm requires only one-dimensional maximization at each boosting step and (c) the resulting estimators can be written explicitly and simply in some practical cases.

KW - Bias reduction

KW - Generalized linear models

KW - Kernel regression

KW - L Boosting

KW - Local quasi-likelihood

KW - Nadaraya - Watson estimator

UR - http://www.scopus.com/inward/record.url?scp=77950689098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950689098&partnerID=8YFLogxK

U2 - 10.1007/s10463-008-0173-5

DO - 10.1007/s10463-008-0173-5

M3 - Article

AN - SCOPUS:77950689098

VL - 62

SP - 235

EP - 248

JO - Annals of the Institute of Statistical Mathematics

JF - Annals of the Institute of Statistical Mathematics

SN - 0020-3157

IS - 2

ER -