Local and omnibus goodness-of-fit tests in classical measurement error models

Handle URI:
http://hdl.handle.net/10754/598222
Title:
Local and omnibus goodness-of-fit tests in classical measurement error models
Authors:
Ma, Yanyuan; Hart, Jeffrey D.; Janicki, Ryan; Carroll, Raymond J.
Abstract:
We consider functional measurement error models, i.e. models where covariates are measured with error and yet no distributional assumptions are made about the mismeasured variable. We propose and study a score-type local test and an orthogonal series-based, omnibus goodness-of-fit test in this context, where no likelihood function is available or calculated-i.e. all the tests are proposed in the semiparametric model framework. We demonstrate that our tests have optimality properties and computational advantages that are similar to those of the classical score tests in the parametric model framework. The test procedures are applicable to several semiparametric extensions of measurement error models, including when the measurement error distribution is estimated non-parametrically as well as for generalized partially linear models. The performance of the local score-type and omnibus goodness-of-fit tests is demonstrated through simulation studies and analysis of a nutrition data set.
Citation:
Ma Y, Hart JD, Janicki R, Carroll RJ (2010) Local and omnibus goodness-of-fit tests in classical measurement error models. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 73: 81–98. Available: http://dx.doi.org/10.1111/j.1467-9868.2010.00751.x.
Publisher:
Wiley-Blackwell
Journal:
Journal of the Royal Statistical Society: Series B (Statistical Methodology)
KAUST Grant Number:
KUS-C1-016-04
Issue Date:
14-Sep-2010
DOI:
10.1111/j.1467-9868.2010.00751.x
PubMed ID:
21339886
PubMed Central ID:
PMC3040518
Type:
Article
ISSN:
1369-7412
Sponsors:
Carroll and Ma's research was supported by a grant from the National Cancer Institute (CA57030). Carroll and Hart's work was also supported by award KUS-C1-016-04, made by King Abdullah University of Science and Technology. Ma's work is supported by National Science Foundation grant DMS-0906341, and Hart's was partially supported by National Science Foundation grant DMS-0604801. Janicki's work was done while at the University of Maryland. He thanks his adviser Professor Abram Kagan for his advice and support.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorMa, Yanyuanen
dc.contributor.authorHart, Jeffrey D.en
dc.contributor.authorJanicki, Ryanen
dc.contributor.authorCarroll, Raymond J.en
dc.date.accessioned2016-02-25T13:39:53Zen
dc.date.available2016-02-25T13:39:53Zen
dc.date.issued2010-09-14en
dc.identifier.citationMa Y, Hart JD, Janicki R, Carroll RJ (2010) Local and omnibus goodness-of-fit tests in classical measurement error models. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 73: 81–98. Available: http://dx.doi.org/10.1111/j.1467-9868.2010.00751.x.en
dc.identifier.issn1369-7412en
dc.identifier.pmid21339886en
dc.identifier.doi10.1111/j.1467-9868.2010.00751.xen
dc.identifier.urihttp://hdl.handle.net/10754/598222en
dc.description.abstractWe consider functional measurement error models, i.e. models where covariates are measured with error and yet no distributional assumptions are made about the mismeasured variable. We propose and study a score-type local test and an orthogonal series-based, omnibus goodness-of-fit test in this context, where no likelihood function is available or calculated-i.e. all the tests are proposed in the semiparametric model framework. We demonstrate that our tests have optimality properties and computational advantages that are similar to those of the classical score tests in the parametric model framework. The test procedures are applicable to several semiparametric extensions of measurement error models, including when the measurement error distribution is estimated non-parametrically as well as for generalized partially linear models. The performance of the local score-type and omnibus goodness-of-fit tests is demonstrated through simulation studies and analysis of a nutrition data set.en
dc.description.sponsorshipCarroll and Ma's research was supported by a grant from the National Cancer Institute (CA57030). Carroll and Hart's work was also supported by award KUS-C1-016-04, made by King Abdullah University of Science and Technology. Ma's work is supported by National Science Foundation grant DMS-0906341, and Hart's was partially supported by National Science Foundation grant DMS-0604801. Janicki's work was done while at the University of Maryland. He thanks his adviser Professor Abram Kagan for his advice and support.en
dc.publisherWiley-Blackwellen
dc.subjectEfficient estimationen
dc.subjectEfficient testingen
dc.subjectErrors in variablesen
dc.subjectGoodness-of-fit testsen
dc.subjectLocal alternativesen
dc.subjectMeasurement erroren
dc.subjectScore testingen
dc.subjectSemiparametric modelsen
dc.titleLocal and omnibus goodness-of-fit tests in classical measurement error modelsen
dc.typeArticleen
dc.identifier.journalJournal of the Royal Statistical Society: Series B (Statistical Methodology)en
dc.identifier.pmcidPMC3040518en
dc.contributor.institutionTexas A&M University, College Station, USA.en
kaust.grant.numberKUS-C1-016-04en

Related articles on PubMed

All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.