Semiparametric Bayesian joint models of multivariate longitudinal and survival data

Tang, Niansheng; Tang, An-Min; Pan, Dongdong

doi:10.1016/j.csda.2014.02.015

Cited by 25 publications

(32 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the piecewise constant hazard model could be employed to specify the prior distribution of the unknown baseline hazard (Zhu et al., ; Huang et al., ; Tang et al., ). But it might lead to a nonsmooth survival function, especially when the time axis is divided into a small number of intervals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian variable selection and estimation in semiparametric joint models of multivariate longitudinal and survival data

2016

Self Cite

View full text Add to dashboard Cite

This paper presents a novel semiparametric joint model for multivariate longitudinal and survival data (SJMLS) by relaxing the normality assumption of the longitudinal outcomes, leaving the baseline hazard functions unspecified and allowing the history of the longitudinal response having an effect on the risk of dropout. Using Bayesian penalized splines to approximate the unspecified baseline hazard function and combining the Gibbs sampler and the Metropolis-Hastings algorithm, we propose a Bayesian Lasso (BLasso) method to simultaneously estimate unknown parameters and select important covariates in SJMLS. Simulation studies are conducted to investigate the finite sample performance of the proposed techniques. An example from the International Breast Cancer Study Group (IBCSG) is used to illustrate the proposed methodologies.

show abstract

Section: Introductionmentioning

confidence: 99%

“…There were a total of 2154 QOL observations in the data set. Chi and Ibrahim (2006), Zhu et al (2012), and Tang et al (2014) analyzed the data set via various parametric/semiparametric JMLSs. However, they did not consider the selection of the potentially important covariates including therapy designs and individual characteristics.…”

Section: Introductionmentioning

confidence: 99%

Bayesian variable selection and estimation in semiparametric joint models of multivariate longitudinal and survival data

2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, over the past 2 decades, statistical methods that can provide a more flexible modelling framework for both the time‐to‐event and longitudinal aspects have emerged. The resulting methodology is called joint modelling (Chi & Ibrahim, ; Rizopoulos, ; Tang & Tang, ; Tang, Tang, & Pan, ). Corresponding software for implementing joint modelling in analysis has also recently become available in mainstream statistical software packages (Gould et al, ).…”

Section: Introductionmentioning

confidence: 99%

A new method for analysing transition to psychosis: Joint modelling of time‐to‐event outcome with time‐dependent predictors

Yuen

Mackinnon

Nelson

2017

Int J Methods Psych Res

View full text Add to dashboard Cite

An active area in psychosis research is the identification of predictors of transition to a psychotic state among those who are assessed as being at high risk of psychosis. Many of the potential predictors are time dependent in the sense that they may change over time and are measured at a number of assessment time points. Examples are various psychopathological measures such as negative symptoms, positive symptoms, depression, and anxiety. Most research in transition to psychosis has not made use of the dynamic nature of these measures, probably because suitable statistical methods and software have not been easily available. However, a relatively new statistical methodology is well suited to include such time-dependent predictors in transition to psychosis analysis. This methodology is called joint modelling and has recently been incorporated in mainstream statistical software. This paper describes this methodology and demonstrates its usefulness using data from one of the pioneering studies on transition to psychosis.

show abstract

“…The most popular choices for the baseline hazard function specification are the parametric forms (e.g. Weibull - Guo and Carlin (2004)) or the piecewise constant approximations (Tang et al, 2014;Baghfalaki and Ganjali, 2015). In seeking the most flexibility as possible we will use an approach rooted on penalized cubic B-spline functions (P-Splines for short).…”

Section: Introductionmentioning

confidence: 99%

A Bayesian Joint Dispersion Model with Flexible Links

Martins

2017

Springer Proceedings in Mathematics &Amp; Statistics

View full text Add to dashboard Cite

The objective is to model longitudinal and survival data jointly taking into account the dependence between the two responses in a real HIV/AIDS dataset using a shared parameter approach inside a Bayesian framework. We propose a linear mixed effects dispersion model to adjust the CD4 longitudinal biomarker data with a between-individual heterogeneity in the mean and variance. In doing so we are relaxing the usual assumption of a common variance for the longitudinal residuals. A hazard regression model is considered in addition to model the time since HIV/AIDS diagnostic until failure, being the coefficients, accounting for the linking between the longitudinal and survival processes, time-varying. This flexibility is specified using Penalized Splines and allows the relationship to vary in time. Because heteroscedasticity may be related with the survival, the standard deviation is considered as a covariate in the hazard model, thus enabling to study the effect of the CD4 counts' stability on the survival. The proposed framework outperforms the most used joint models, highlighting the importance in correctly taking account the individual heterogeneity for the measurement errors variance and the evolution of the disease over time in bringing new insights to better understand this biomarker-survival relation.

show abstract

Semiparametric Bayesian joint models of multivariate longitudinal and survival data

Cited by 25 publications

References 40 publications

Bayesian variable selection and estimation in semiparametric joint models of multivariate longitudinal and survival data

Bayesian variable selection and estimation in semiparametric joint models of multivariate longitudinal and survival data

A new method for analysing transition to psychosis: Joint modelling of time‐to‐event outcome with time‐dependent predictors

A Bayesian Joint Dispersion Model with Flexible Links

Contact Info

Product

Resources

About