A lack-of-fit test for heteroscedastic regression models via cosine-series smoothers

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, a test is derived to assess the validity of heteroscedastic nonlinear regression models by a non-parametric cosine regression method. For order selection, the paper proposes a data-driven method that uses the parametric null model optimal order. This method yields a test that is asymptotically normally distributed under the null hypothesis and is consistent against any fixed alternative. Simulation studies that test the lack of fit of a generalized linear model are conducted to compare the performance of the proposed test with that of an existing non-parametric kernel test. A dataset of esterase levels is used to demonstrate the proposed method in practice.

Original languageEnglish (US)
Pages (from-to)477-489
Number of pages13
JournalAustralian and New Zealand Journal of Statistics
Volume45
Issue number4
StatePublished - Dec 2003
Externally publishedYes

Fingerprint

Lack-of-fit Test
Heteroscedastic Regression
Heteroscedastic Model
Regression Model
Series
Lack of Fit
Order Selection
Nonlinear Regression Model
Generalized Linear Model
Data-driven
Null hypothesis
Null
Regression
Regression model
Simulation Study
kernel
Alternatives
Demonstrate

Keywords

  • Cosine-series smoother
  • Fit-comparison test
  • Order selection
  • Quasi-likelihood estimator

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

A lack-of-fit test for heteroscedastic regression models via cosine-series smoothers. / Li, Chin-Shang.

In: Australian and New Zealand Journal of Statistics, Vol. 45, No. 4, 12.2003, p. 477-489.

Research output: Contribution to journalArticle

@article{87d8eff7772c4bd7b48ff1e7adb88d12,
title = "A lack-of-fit test for heteroscedastic regression models via cosine-series smoothers",
abstract = "In this paper, a test is derived to assess the validity of heteroscedastic nonlinear regression models by a non-parametric cosine regression method. For order selection, the paper proposes a data-driven method that uses the parametric null model optimal order. This method yields a test that is asymptotically normally distributed under the null hypothesis and is consistent against any fixed alternative. Simulation studies that test the lack of fit of a generalized linear model are conducted to compare the performance of the proposed test with that of an existing non-parametric kernel test. A dataset of esterase levels is used to demonstrate the proposed method in practice.",
keywords = "Cosine-series smoother, Fit-comparison test, Order selection, Quasi-likelihood estimator",
author = "Chin-Shang Li",
year = "2003",
month = "12",
language = "English (US)",
volume = "45",
pages = "477--489",
journal = "Australian and New Zealand Journal of Statistics",
issn = "1369-1473",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - A lack-of-fit test for heteroscedastic regression models via cosine-series smoothers

AU - Li, Chin-Shang

PY - 2003/12

Y1 - 2003/12

N2 - In this paper, a test is derived to assess the validity of heteroscedastic nonlinear regression models by a non-parametric cosine regression method. For order selection, the paper proposes a data-driven method that uses the parametric null model optimal order. This method yields a test that is asymptotically normally distributed under the null hypothesis and is consistent against any fixed alternative. Simulation studies that test the lack of fit of a generalized linear model are conducted to compare the performance of the proposed test with that of an existing non-parametric kernel test. A dataset of esterase levels is used to demonstrate the proposed method in practice.

AB - In this paper, a test is derived to assess the validity of heteroscedastic nonlinear regression models by a non-parametric cosine regression method. For order selection, the paper proposes a data-driven method that uses the parametric null model optimal order. This method yields a test that is asymptotically normally distributed under the null hypothesis and is consistent against any fixed alternative. Simulation studies that test the lack of fit of a generalized linear model are conducted to compare the performance of the proposed test with that of an existing non-parametric kernel test. A dataset of esterase levels is used to demonstrate the proposed method in practice.

KW - Cosine-series smoother

KW - Fit-comparison test

KW - Order selection

KW - Quasi-likelihood estimator

UR - http://www.scopus.com/inward/record.url?scp=0345447591&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0345447591&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0345447591

VL - 45

SP - 477

EP - 489

JO - Australian and New Zealand Journal of Statistics

JF - Australian and New Zealand Journal of Statistics

SN - 1369-1473

IS - 4

ER -