Parametric variable selection in generalized partially linear models with an application to assess condom use by HIV‐infected patients
Identifieur interne : 000871 ( Main/Exploration ); précédent : 000870; suivant : 000872Parametric variable selection in generalized partially linear models with an application to assess condom use by HIV‐infected patients
Auteurs : Chenlei Leng [Singapour] ; Hua Liang [États-Unis] ; Neil Martinson [Afrique du Sud, États-Unis]Source :
- Statistics in Medicine [ 0277-6715 ] ; 2011-07-20.
Descripteurs français
- Wicri :
- topic : Droit d'auteur, Santé génésique, Simulation.
English descriptors
- KwdEn :
- Absolute deviation, Adaptive lasso, American journal, Asymptotic, Asymptotic covariance matrix, Asymptotic normality, Average number, Bandwidth, Basis functions, Cell count, Cell counts, Chronic kidney disease, Condom, Condom effectiveness, Consistent condom, Consistent estimator, Continuous predictors, Convergence rate, Copyright, Covariance, Covariance matrix, Covariate, Covariates, England journal, Estimation, Estimation accuracy, Estimator, Full model, Future course, Generalized additive model, Generalized additive models, Gplm, Great interest, Higher levels, Important predictors, Interesting question, John wiley sons, Lasso, Least squares approximation, Leng, Liang, Library mgcv, Likelihood approach, Likelihood method, Linear models, Link function, Logistic regression, Longitudinal data, Martinson, Martinson table, Matrix, Model complexity, Model selection, Multiple covariates, Multivariate analysis, Nonparametric, Optimal bandwidth, Oracle, Oracle procedure, Oracle properties, Oracle property, Other hand, Parametric, Parametric components, Parametric part, Phru, Phru data, Phru study, Policy makers, Predictor, Preliminary estimate, Preliminary estimates, Prevention programs, Proportional hazards model, Regression spline, Regular partners, Reproductive health, Research unit, Right panel, Sample size, Sample size increases, Sample sizes, Semiparametric, Semiparametric model selection, Semiparametric modeling, Semiparametric models, Semiparametric regression, Sexual behavior, Sexual transmission, Signal strength, Simulation, Simulation studies, Simulation study, Spline, Spline estimation, Spline method, Square errors, Standard error, Standard errors, Statist, True model, True model structure, Tted, Variable selection, Variable selection procedure, Variable selection procedures, Zhang.
- Teeft :
- Absolute deviation, Adaptive lasso, American journal, Asymptotic, Asymptotic covariance matrix, Asymptotic normality, Average number, Bandwidth, Basis functions, Cell count, Cell counts, Chronic kidney disease, Condom, Condom effectiveness, Consistent condom, Consistent estimator, Continuous predictors, Convergence rate, Copyright, Covariance, Covariance matrix, Covariate, Covariates, England journal, Estimation, Estimation accuracy, Estimator, Full model, Future course, Generalized additive model, Generalized additive models, Gplm, Great interest, Higher levels, Important predictors, Interesting question, John wiley sons, Lasso, Least squares approximation, Leng, Liang, Library mgcv, Likelihood approach, Likelihood method, Linear models, Link function, Logistic regression, Longitudinal data, Martinson, Martinson table, Matrix, Model complexity, Model selection, Multiple covariates, Multivariate analysis, Nonparametric, Optimal bandwidth, Oracle, Oracle procedure, Oracle properties, Oracle property, Other hand, Parametric, Parametric components, Parametric part, Phru, Phru data, Phru study, Policy makers, Predictor, Preliminary estimate, Preliminary estimates, Prevention programs, Proportional hazards model, Regression spline, Regular partners, Reproductive health, Research unit, Right panel, Sample size, Sample size increases, Sample sizes, Semiparametric, Semiparametric model selection, Semiparametric modeling, Semiparametric models, Semiparametric regression, Sexual behavior, Sexual transmission, Signal strength, Simulation, Simulation studies, Simulation study, Spline, Spline estimation, Spline method, Square errors, Standard error, Standard errors, Statist, True model, True model structure, Tted, Variable selection, Variable selection procedure, Variable selection procedures, Zhang.
Abstract
To study significant predictors of condom use in HIV‐infected adults, we propose the use of generalized partially linear models and develop a variable selection procedure incorporating a least squares approximation. Local polynomial regression and spline smoothing techniques are used to estimate the baseline nonparametric function. The asymptotic normality of the resulting estimate is established. We further demonstrate that, with the proper choice of the penalty functions and the regularization parameter, the resulting estimate performs as well as an oracle procedure. Finite sample performance of the proposed inference procedure is assessed by Monte Carlo simulation studies. An application to assess condom use by HIV‐infected patients gains some interesting results, which cannot be obtained when an ordinary logistic model is used. Copyright © 2011 John Wiley & Sons, Ltd.
Url:
DOI: 10.1002/sim.4233
Affiliations:
- Afrique du Sud, Singapour, États-Unis
- Gauteng
- Johannesbourg
- Université du Witwatersrand, Université nationale de Singapour
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000807
- to stream Istex, to step Curation: 000807
- to stream Istex, to step Checkpoint: 000093
- to stream Main, to step Merge: 000874
- to stream Main, to step Curation: 000871
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Parametric variable selection in generalized partially linear models with an application to assess condom use by HIV‐infected patients</title>
<author><name sortKey="Leng, Chenlei" sort="Leng, Chenlei" uniqKey="Leng C" first="Chenlei" last="Leng">Chenlei Leng</name>
</author>
<author><name sortKey="Liang, Hua" sort="Liang, Hua" uniqKey="Liang H" first="Hua" last="Liang">Hua Liang</name>
</author>
<author><name sortKey="Martinson, Neil" sort="Martinson, Neil" uniqKey="Martinson N" first="Neil" last="Martinson">Neil Martinson</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:6077195E49E00688B84D2FF3D7D1B858F55F7544</idno>
<date when="2011" year="2011">2011</date>
<idno type="doi">10.1002/sim.4233</idno>
<idno type="url">https://api.istex.fr/document/6077195E49E00688B84D2FF3D7D1B858F55F7544/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000807</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000807</idno>
<idno type="wicri:Area/Istex/Curation">000807</idno>
<idno type="wicri:Area/Istex/Checkpoint">000093</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000093</idno>
<idno type="wicri:doubleKey">0277-6715:2011:Leng C:parametric:variable:selection</idno>
<idno type="wicri:Area/Main/Merge">000874</idno>
<idno type="wicri:Area/Main/Curation">000871</idno>
<idno type="wicri:Area/Main/Exploration">000871</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Parametric variable selection in generalized partially linear models with an application to assess condom use by HIV‐infected patients</title>
<author><name sortKey="Leng, Chenlei" sort="Leng, Chenlei" uniqKey="Leng C" first="Chenlei" last="Leng">Chenlei Leng</name>
<affiliation wicri:level="4"><country xml:lang="fr">Singapour</country>
<wicri:regionArea>Department of Statistics and Applied Probability, National University of Singapore</wicri:regionArea>
<orgName type="university">Université nationale de Singapour</orgName>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr">Singapour</country>
<wicri:regionArea>Department of Statistics and Applied Probability, National University of Singapore</wicri:regionArea>
<orgName type="university">Université nationale de Singapour</orgName>
</affiliation>
</author>
<author><name sortKey="Liang, Hua" sort="Liang, Hua" uniqKey="Liang H" first="Hua" last="Liang">Hua Liang</name>
<affiliation wicri:level="1"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Biostatistics and Computational Biology, University of Rochester Medical Center, Rochester, NY 14642</wicri:regionArea>
<wicri:noRegion>NY 14642</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Martinson, Neil" sort="Martinson, Neil" uniqKey="Martinson N" first="Neil" last="Martinson">Neil Martinson</name>
<affiliation wicri:level="4"><country xml:lang="fr">Afrique du Sud</country>
<wicri:regionArea>Perinatal HIV Research Unit, University of the Witwatersrand, Johannesburg</wicri:regionArea>
<orgName type="university">Université du Witwatersrand</orgName>
<placeName><settlement type="city">Johannesbourg</settlement>
<region type="region" nuts="2">Gauteng</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Johns Hopkins University, School of Medicine, Baltimore, MD 21231</wicri:regionArea>
<wicri:noRegion>MD 21231</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j" type="main">Statistics in Medicine</title>
<title level="j" type="alt">STATISTICS IN MEDICINE</title>
<idno type="ISSN">0277-6715</idno>
<idno type="eISSN">1097-0258</idno>
<imprint><biblScope unit="vol">30</biblScope>
<biblScope unit="issue">16</biblScope>
<biblScope unit="page" from="2015">2015</biblScope>
<biblScope unit="page" to="2027">2027</biblScope>
<biblScope unit="page-count">13</biblScope>
<publisher>John Wiley & Sons, Ltd.</publisher>
<pubPlace>Chichester, UK</pubPlace>
<date type="published" when="2011-07-20">2011-07-20</date>
</imprint>
<idno type="ISSN">0277-6715</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0277-6715</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Absolute deviation</term>
<term>Adaptive lasso</term>
<term>American journal</term>
<term>Asymptotic</term>
<term>Asymptotic covariance matrix</term>
<term>Asymptotic normality</term>
<term>Average number</term>
<term>Bandwidth</term>
<term>Basis functions</term>
<term>Cell count</term>
<term>Cell counts</term>
<term>Chronic kidney disease</term>
<term>Condom</term>
<term>Condom effectiveness</term>
<term>Consistent condom</term>
<term>Consistent estimator</term>
<term>Continuous predictors</term>
<term>Convergence rate</term>
<term>Copyright</term>
<term>Covariance</term>
<term>Covariance matrix</term>
<term>Covariate</term>
<term>Covariates</term>
<term>England journal</term>
<term>Estimation</term>
<term>Estimation accuracy</term>
<term>Estimator</term>
<term>Full model</term>
<term>Future course</term>
<term>Generalized additive model</term>
<term>Generalized additive models</term>
<term>Gplm</term>
<term>Great interest</term>
<term>Higher levels</term>
<term>Important predictors</term>
<term>Interesting question</term>
<term>John wiley sons</term>
<term>Lasso</term>
<term>Least squares approximation</term>
<term>Leng</term>
<term>Liang</term>
<term>Library mgcv</term>
<term>Likelihood approach</term>
<term>Likelihood method</term>
<term>Linear models</term>
<term>Link function</term>
<term>Logistic regression</term>
<term>Longitudinal data</term>
<term>Martinson</term>
<term>Martinson table</term>
<term>Matrix</term>
<term>Model complexity</term>
<term>Model selection</term>
<term>Multiple covariates</term>
<term>Multivariate analysis</term>
<term>Nonparametric</term>
<term>Optimal bandwidth</term>
<term>Oracle</term>
<term>Oracle procedure</term>
<term>Oracle properties</term>
<term>Oracle property</term>
<term>Other hand</term>
<term>Parametric</term>
<term>Parametric components</term>
<term>Parametric part</term>
<term>Phru</term>
<term>Phru data</term>
<term>Phru study</term>
<term>Policy makers</term>
<term>Predictor</term>
<term>Preliminary estimate</term>
<term>Preliminary estimates</term>
<term>Prevention programs</term>
<term>Proportional hazards model</term>
<term>Regression spline</term>
<term>Regular partners</term>
<term>Reproductive health</term>
<term>Research unit</term>
<term>Right panel</term>
<term>Sample size</term>
<term>Sample size increases</term>
<term>Sample sizes</term>
<term>Semiparametric</term>
<term>Semiparametric model selection</term>
<term>Semiparametric modeling</term>
<term>Semiparametric models</term>
<term>Semiparametric regression</term>
<term>Sexual behavior</term>
<term>Sexual transmission</term>
<term>Signal strength</term>
<term>Simulation</term>
<term>Simulation studies</term>
<term>Simulation study</term>
<term>Spline</term>
<term>Spline estimation</term>
<term>Spline method</term>
<term>Square errors</term>
<term>Standard error</term>
<term>Standard errors</term>
<term>Statist</term>
<term>True model</term>
<term>True model structure</term>
<term>Tted</term>
<term>Variable selection</term>
<term>Variable selection procedure</term>
<term>Variable selection procedures</term>
<term>Zhang</term>
</keywords>
<keywords scheme="Teeft" xml:lang="en"><term>Absolute deviation</term>
<term>Adaptive lasso</term>
<term>American journal</term>
<term>Asymptotic</term>
<term>Asymptotic covariance matrix</term>
<term>Asymptotic normality</term>
<term>Average number</term>
<term>Bandwidth</term>
<term>Basis functions</term>
<term>Cell count</term>
<term>Cell counts</term>
<term>Chronic kidney disease</term>
<term>Condom</term>
<term>Condom effectiveness</term>
<term>Consistent condom</term>
<term>Consistent estimator</term>
<term>Continuous predictors</term>
<term>Convergence rate</term>
<term>Copyright</term>
<term>Covariance</term>
<term>Covariance matrix</term>
<term>Covariate</term>
<term>Covariates</term>
<term>England journal</term>
<term>Estimation</term>
<term>Estimation accuracy</term>
<term>Estimator</term>
<term>Full model</term>
<term>Future course</term>
<term>Generalized additive model</term>
<term>Generalized additive models</term>
<term>Gplm</term>
<term>Great interest</term>
<term>Higher levels</term>
<term>Important predictors</term>
<term>Interesting question</term>
<term>John wiley sons</term>
<term>Lasso</term>
<term>Least squares approximation</term>
<term>Leng</term>
<term>Liang</term>
<term>Library mgcv</term>
<term>Likelihood approach</term>
<term>Likelihood method</term>
<term>Linear models</term>
<term>Link function</term>
<term>Logistic regression</term>
<term>Longitudinal data</term>
<term>Martinson</term>
<term>Martinson table</term>
<term>Matrix</term>
<term>Model complexity</term>
<term>Model selection</term>
<term>Multiple covariates</term>
<term>Multivariate analysis</term>
<term>Nonparametric</term>
<term>Optimal bandwidth</term>
<term>Oracle</term>
<term>Oracle procedure</term>
<term>Oracle properties</term>
<term>Oracle property</term>
<term>Other hand</term>
<term>Parametric</term>
<term>Parametric components</term>
<term>Parametric part</term>
<term>Phru</term>
<term>Phru data</term>
<term>Phru study</term>
<term>Policy makers</term>
<term>Predictor</term>
<term>Preliminary estimate</term>
<term>Preliminary estimates</term>
<term>Prevention programs</term>
<term>Proportional hazards model</term>
<term>Regression spline</term>
<term>Regular partners</term>
<term>Reproductive health</term>
<term>Research unit</term>
<term>Right panel</term>
<term>Sample size</term>
<term>Sample size increases</term>
<term>Sample sizes</term>
<term>Semiparametric</term>
<term>Semiparametric model selection</term>
<term>Semiparametric modeling</term>
<term>Semiparametric models</term>
<term>Semiparametric regression</term>
<term>Sexual behavior</term>
<term>Sexual transmission</term>
<term>Signal strength</term>
<term>Simulation</term>
<term>Simulation studies</term>
<term>Simulation study</term>
<term>Spline</term>
<term>Spline estimation</term>
<term>Spline method</term>
<term>Square errors</term>
<term>Standard error</term>
<term>Standard errors</term>
<term>Statist</term>
<term>True model</term>
<term>True model structure</term>
<term>Tted</term>
<term>Variable selection</term>
<term>Variable selection procedure</term>
<term>Variable selection procedures</term>
<term>Zhang</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Droit d'auteur</term>
<term>Santé génésique</term>
<term>Simulation</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">To study significant predictors of condom use in HIV‐infected adults, we propose the use of generalized partially linear models and develop a variable selection procedure incorporating a least squares approximation. Local polynomial regression and spline smoothing techniques are used to estimate the baseline nonparametric function. The asymptotic normality of the resulting estimate is established. We further demonstrate that, with the proper choice of the penalty functions and the regularization parameter, the resulting estimate performs as well as an oracle procedure. Finite sample performance of the proposed inference procedure is assessed by Monte Carlo simulation studies. An application to assess condom use by HIV‐infected patients gains some interesting results, which cannot be obtained when an ordinary logistic model is used. Copyright © 2011 John Wiley & Sons, Ltd.</div>
</front>
</TEI>
<affiliations><list><country><li>Afrique du Sud</li>
<li>Singapour</li>
<li>États-Unis</li>
</country>
<region><li>Gauteng</li>
</region>
<settlement><li>Johannesbourg</li>
</settlement>
<orgName><li>Université du Witwatersrand</li>
<li>Université nationale de Singapour</li>
</orgName>
</list>
<tree><country name="Singapour"><noRegion><name sortKey="Leng, Chenlei" sort="Leng, Chenlei" uniqKey="Leng C" first="Chenlei" last="Leng">Chenlei Leng</name>
</noRegion>
<name sortKey="Leng, Chenlei" sort="Leng, Chenlei" uniqKey="Leng C" first="Chenlei" last="Leng">Chenlei Leng</name>
</country>
<country name="États-Unis"><noRegion><name sortKey="Liang, Hua" sort="Liang, Hua" uniqKey="Liang H" first="Hua" last="Liang">Hua Liang</name>
</noRegion>
<name sortKey="Martinson, Neil" sort="Martinson, Neil" uniqKey="Martinson N" first="Neil" last="Martinson">Neil Martinson</name>
</country>
<country name="Afrique du Sud"><region name="Gauteng"><name sortKey="Martinson, Neil" sort="Martinson, Neil" uniqKey="Martinson N" first="Neil" last="Martinson">Neil Martinson</name>
</region>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/SidaGhanaV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000871 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000871 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Sante |area= SidaGhanaV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:6077195E49E00688B84D2FF3D7D1B858F55F7544 |texte= Parametric variable selection in generalized partially linear models with an application to assess condom use by HIV‐infected patients }}
This area was generated with Dilib version V0.6.31. |