Analysis of multivariate longitudinal data using dynamic lasso-regularized copula models with application to large pediatric cardiovascular studies
This work was authored as part of the Contributor's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 USC. 105, no copyright protection is available for such works under US Law.
| Publié dans: | Journal of applied statistics. - 1991. - 50(2023), 3 vom: 23., Seite 631-658 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , , , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2023
|
| Accès à la collection: | Journal of applied statistics |
| Sujets: | Journal Article Dynamic copula model functional parameter lasso-regularized spline estimator multivariate longitudinal data statistical machine learning time-varying covariate |
| Résumé: | This work was authored as part of the Contributor's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 USC. 105, no copyright protection is available for such works under US Law. The National Heart, Lung and Blood Institute Growth and Health Study (NGHS) is a large longitudinal study of childhood health. A main objective of the study is to estimate the joint distributions of cardiovascular risk outcomes at any two time points conditioning on a large number of covariates. Existing multivariate longitudinal methods are not suitable for outcomes at multiple time points. We present a dynamic copula approach for estimating an outcome's joint distributions at two time points given a large number of time-varying covariates. Our models depend on the outcome's time-varying distributions at one time point, the bivariate copula densities and the functional copula parameters. We develop a three-step procedure for variable selection and estimation, which selects the influential covariates using a machine learning procedure based on spline Lasso-regularized least squares, computes the outcome's single-time distribution using splines, and estimates the functional copula parameter of the dynamic copula models. Pointwise confidence intervals are constructed through the resampling-subject bootstrap. We apply our procedure to the NGHS cardiovascular risk data and illustrate the clinical interpretations of the conditional distributions of a set of risk outcomes. We demonstrate the statistical properties of the dynamic models and estimation procedure through a simulation study |
|---|---|
| Description: | Date Revised 24.02.2023 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
| ISSN: | 0266-4763 |
| DOI: | 10.1080/02664763.2021.1937581 |