2010
DOI: 10.1198/jasa.2010.tm09572
|View full text |Cite
|
Sign up to set email alerts
|

Modeling Longitudinal Data Using a Pair-Copula Decomposition of Serial Dependence

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
157
0
4

Year Published

2012
2012
2017
2017

Publication Types

Select...
7

Relationship

2
5

Authors

Journals

citations
Cited by 160 publications
(161 citation statements)
references
References 33 publications
0
157
0
4
Order By: Relevance
“…At the moment only selection procedures within specified D-vine structures exist. Min and Czado (2010b) use reversible jump MCMC to simplify a D-vine with specific single pair-copula family by discovering conditional independences, while Smith et al (2010) use indicator variables for identifying conditional independence in a Bayesian setup. The goal of this paper is to provide a comprehensive solution to the selection of C-vines by identifying an appropriate C-vine structure and selecting a fitting pair-copula family.…”
Section: Introductionmentioning
confidence: 99%
“…At the moment only selection procedures within specified D-vine structures exist. Min and Czado (2010b) use reversible jump MCMC to simplify a D-vine with specific single pair-copula family by discovering conditional independences, while Smith et al (2010) use indicator variables for identifying conditional independence in a Bayesian setup. The goal of this paper is to provide a comprehensive solution to the selection of C-vines by identifying an appropriate C-vine structure and selecting a fitting pair-copula family.…”
Section: Introductionmentioning
confidence: 99%
“…A goodness of fit test can be performed to choose the combination of the pair-copulae that best fits to data. Smith et al (2010) , Smith (2015) and Panagiotelis, Czado, and Harry (2012) use a vinecopula approach to model the dependence structure for longitudinal data and have shown encouraging results on the goodness of fit achieved in an empirical analysis on headache severity. Different vine decomposition, such as regular-vine (R-vine), canonicalvine (C-vine) and drawable vine (D-vine), have been proposed to describe specific dependence between the variables.…”
Section: The D-vine Copulamentioning
confidence: 99%
“…For modelling the time dependence in longitudinal data, in this paper we choose a copula approach, analogously to Smith, Min, Almeida, and Czado (2010) and Meade and Islam (2010) , because it is a simple method to estimate multivariate models when the marginal responses are given. Furthermore, the copula approach is particularly suitable to model different kinds of dependence structures.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations