×

A semiparametric approach to simultaneous covariance estimation for bivariate sparse longitudinal data. (English) Zbl 1419.62334

Summary: Estimation of the covariance structure for irregular sparse longitudinal data has been studied by many authors in recent years but typically using fully parametric specifications. In addition, when data are collected from several groups over time, it is known that assuming the same or completely different covariance matrices over groups can lead to loss of efficiency and/or bias. Nonparametric approaches have been proposed for estimating the covariance matrix for regular univariate longitudinal data by sharing information across the groups under study. For the irregular case, with longitudinal measurements that are bivariate or multivariate, modeling becomes more difficult. In this article, to model bivariate sparse longitudinal data from several groups, we propose a flexible covariance structure via a novel matrix stick-breaking process for the residual covariance structure and a Dirichlet process mixture of normals for the random effects. Simulation studies are performed to investigate the effectiveness of the proposed approach over more traditional approaches. We also analyze a subset of Framingham Heart Study data to examine how the blood pressure trajectories and covariance structures differ for the patients from different BMI groups (high, medium, and low) at baseline.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62F15 Bayesian inference
62J12 Generalized linear models (logistic models)

Software:

MIXED; SemiPar
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Bandyopadhyay, Linear mixed models for skew-normal/ independent bivariate responses with an application to periodontal disease, Statistics in Medicine 29 pp 2643– (2010) · doi:10.1002/sim.4031
[2] Brooks, General methods for monitoring convergence of iterative simulations, Journal of Computational and Graphical Statistics 7 pp 434– (1998)
[3] Celeux, Deviance information criteria for missing data models, Bayesian Analysis 1 pp 651– (2006) · Zbl 1331.62329 · doi:10.1214/06-BA122
[4] Daniels , M. J. Hogan , J. W. 2008 Missing Data in Longitudinal Studies: Strategies for Bayesian Modeling and Sensitivity Analysis · Zbl 1165.62023
[5] Daniels, Bayesian analysis of covariance matrices and dynamic models for longitudinal data, Biometrika 89 pp 553– (2002) · Zbl 1036.62019 · doi:10.1093/biomet/89.3.553
[6] Das, Genome-wide association studies for bivariate sparse longitudinal data, Human Heredity 72 pp 110– (2011) · doi:10.1159/000330781
[7] Das, A Bayesian framework for functional mapping through joint modeling of longitudinal and time-to-event data, International Journal of Plant Genomics 2012 pp 1– (2012) · doi:10.1155/2012/680634
[8] Das, Statistics in Medicine 32 pp 509– (2013a) · Zbl 1016.81039 · doi:10.1002/sim.5535
[9] Das, A Bayesian semi-parametric model for bivariate sparse longitudinal data, Statistics in Medicine 32 pp 3899– (2013b) · doi:10.1002/sim.5790
[10] Dunson, The matrix stick-breaking process: Flexible Bayes meta-analysis, Journal of American Statistical Association 103 pp 317– (2008) · Zbl 1471.62502 · doi:10.1198/016214507000001364
[11] Durban, Simple fitting of subject-specific curves for longitudinal data, Statistics in Medicine 24 pp 1153– (2005) · doi:10.1002/sim.1991
[12] Escobar, Bayesian density estimation and inference using mixtures, Journal of the American Statistical Association 90 pp 577– (1995) · Zbl 0826.62021 · doi:10.1080/01621459.1995.10476550
[13] Gaskins, A nonparametric prior for simultaneous covariance estimation, Biometrika 100 pp 125– (2012) · Zbl 1452.62371 · doi:10.1093/biomet/ass060
[14] Ghosh, Semiparametric Bayesian approach to multivariate longitudinal data, Australian and New Zealand Journal of Statistics 52 pp 275– (2010) · Zbl 1373.62381 · doi:10.1111/j.1467-842X.2010.00581.x
[15] Ishwaran, Gibbs sampling methods for stick-breaking priors, Journal of American Statistical Association 96 pp 161– (2001) · Zbl 1014.62006 · doi:10.1198/016214501750332758
[16] MacEachern, Estimating mixture of Dirichlet process models, Journal of Computational and Graphical Statistics 6 pp 223– (1998) · Zbl 0918.62064
[17] Pan, On modelling mean-covariance structures in longitudinal studies, Biometrika 90 pp 239– (2003) · Zbl 1039.62068 · doi:10.1093/biomet/90.1.239
[18] Pourahmadi, Joint mean-covariance model with applications to longitudinal data: Unconstrained parameterisation, Biometrika 86 pp 677– (1999) · Zbl 0949.62066 · doi:10.1093/biomet/86.3.677
[19] Ruppert, Semiparametric Regression (2003) · Zbl 1038.62042 · doi:10.1017/CBO9780511755453
[20] Sethuraman, A constructive definition of Dirichlet priors, Statistica Sinica 4 pp 639– (1994) · Zbl 0823.62007
[21] Sithole, Bivariate longitudinal model for detecting prescribing change in two drugs simultaneously with correlated errors, Journal of Applied Statistics 34 pp 339– (2007) · Zbl 1156.62368 · doi:10.1080/02664760601005020
[22] Sy, A stochastic model for the analysis of bivariate longitudinal AIDS data, Biometrics 53 pp 542– (1997) · Zbl 0881.62122 · doi:10.2307/2533956
[23] Thiebaut, Bivariate linear mixed models using SAS PROC MIXED, Computer Methods and Programs in Biomedicine 69 pp 249– (2002) · Zbl 05462737 · doi:10.1016/S0169-2607(02)00017-2
[24] Wolk, Obesity, sleep apnea and hypertension, Hypertension 42 pp 1067– (2003) · doi:10.1161/01.HYP.0000101686.98973.A3
[25] Wu, Nonparametric estimation of large covariance matrices for longitudinal data, Biometrika 90 pp 831– (2003) · Zbl 1436.62347 · doi:10.1093/biomet/90.4.831
[26] World Health Organization 1995 Physical Status: The Use and Interpretation of Anthropometry http://www.who.int/bmi/index
[27] Yang, Estimation of a covariance matrix using the reference prior, The Annals of Statistics 22 pp 1195– (1994) · Zbl 0819.62013 · doi:10.1214/aos/1176325625
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.