Analysis of generalized semiparametric mixed varying‐coefficients models for longitudinal data. Issue 3 (1st May 2019)
- Record Type:
- Journal Article
- Title:
- Analysis of generalized semiparametric mixed varying‐coefficients models for longitudinal data. Issue 3 (1st May 2019)
- Main Title:
- Analysis of generalized semiparametric mixed varying‐coefficients models for longitudinal data
- Authors:
- Sun, Yanqing
Qi, Li
Heng, Fei
Gilbert, Peter B. - Abstract:
- Abstract: The generalized semiparametric mixed varying‐coefficient effects model for longitudinal data can accommodate a variety of link functions and flexibly model different types of covariate effects, including time‐constant, time‐varying and covariate‐varying effects. The time‐varying effects are unspecified functions of time and the covariate‐varying effects are nonparametric functions of a possibly time‐dependent exposure variable. A semiparametric estimation procedure is developed that uses local linear smoothing and profile weighted least squares, which requires smoothing in the two different and yet connected domains of time and the time‐dependent exposure variable. The asymptotic properties of the estimators of both nonparametric and parametric effects are investigated. In addition, hypothesis testing procedures are developed to examine the covariate effects. The finite‐sample properties of the proposed estimators and testing procedures are examined through simulations, indicating satisfactory performances. The proposed methods are applied to analyze the AIDS Clinical Trial Group 244 clinical trial to investigate the effects of antiretroviral treatment switching in HIV‐infected patients before and after developing the T215Y antiretroviral drug resistance mutation. The Canadian Journal of Statistics 47: 352–373; 2019 © 2019 Statistical Society of Canada Résumé: Le modèle semi‐paramétrique généralisé à effets mixtes et coefficients variables pour les donnéesAbstract: The generalized semiparametric mixed varying‐coefficient effects model for longitudinal data can accommodate a variety of link functions and flexibly model different types of covariate effects, including time‐constant, time‐varying and covariate‐varying effects. The time‐varying effects are unspecified functions of time and the covariate‐varying effects are nonparametric functions of a possibly time‐dependent exposure variable. A semiparametric estimation procedure is developed that uses local linear smoothing and profile weighted least squares, which requires smoothing in the two different and yet connected domains of time and the time‐dependent exposure variable. The asymptotic properties of the estimators of both nonparametric and parametric effects are investigated. In addition, hypothesis testing procedures are developed to examine the covariate effects. The finite‐sample properties of the proposed estimators and testing procedures are examined through simulations, indicating satisfactory performances. The proposed methods are applied to analyze the AIDS Clinical Trial Group 244 clinical trial to investigate the effects of antiretroviral treatment switching in HIV‐infected patients before and after developing the T215Y antiretroviral drug resistance mutation. The Canadian Journal of Statistics 47: 352–373; 2019 © 2019 Statistical Society of Canada Résumé: Le modèle semi‐paramétrique généralisé à effets mixtes et coefficients variables pour les données longitudinales peut accommoder une variété de fonctions liens et offrir la flexibilité de modéliser plusieurs types d'effets, notamment ceux constants dans le temps, variables dans le temps, ou encore variant selon des covariables. Alors que les effets variant dans le temps sont des fonctions non spécifiées du temps, les effets variant selon des covariables sont des fonctions non paramétriques qui peuvent dépendre d'une variable d'exposition elle‐même dépendante du temps. Les auteurs développent une procédure d'estimation semi‐paramétrique basée sur du lissage localement linéaire et un profil de moindres carrés pondérés, ce qui nécessite du lissage dans les domaines différents mais liés du temps et de la variable d'exposition qui dépend du temps. Ils étudient les propriétés asymptotiques des estimateurs des effets paramétriques et non paramétriques, puis développent des procédures de tests d'hypothèse pour examiner l'effet des covariables. Les auteurs examinent les propriétés des estimateurs proposés sur des échantillons finis à l'aide de simulations et observent des performances satisfaisantes. Ils appliquent finalement leur méthode à l'étude clinique ACTG 244 afin d'étudier les effets d'un changement de traitement antirétroviral chez les patients atteints du VIH avant et après le développement de la mutation de résistance aux antiviraux T215Y. La revue canadienne de statistique 47: 352–373; 2019 © 2019 Société statistique du Canada … (more)
- Is Part Of:
- Canadian journal of statistics. Volume 47:Issue 3(2019)
- Journal:
- Canadian journal of statistics
- Issue:
- Volume 47:Issue 3(2019)
- Issue Display:
- Volume 47, Issue 3 (2019)
- Year:
- 2019
- Volume:
- 47
- Issue:
- 3
- Issue Sort Value:
- 2019-0047-0003-0000
- Page Start:
- 352
- Page End:
- 373
- Publication Date:
- 2019-05-01
- Subjects:
- Link function -- local linear smoothing -- profile weighted least squares -- testing covariate‐varying effects -- varying‐coefficient effects
Mathematical statistics -- Periodicals
519.5 - Journal URLs:
- http://archimede.mat.ulaval.ca/cjs/ ↗
http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)1708-945X/issues ↗
http://www.jstor.org/journals/03195724.html ↗
http://onlinelibrary.wiley.com/ ↗
http://www.ingentaconnect.com/content/ssc/cjs ↗
http://www.mat.ulaval.ca/rcs/indexe.shtml ↗ - DOI:
- 10.1002/cjs.11498 ↗
- Languages:
- English
- ISSNs:
- 0319-5724
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3035.760000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 11361.xml