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

2016 ◽  
Vol 59 (1) ◽  
pp. 57-78 ◽  
Author(s):  
An-Min Tang ◽  
Xingqiu Zhao ◽  
Nian-Sheng Tang
Keyword(s):  
Variable Selection ◽  
Survival Data ◽  
Bayesian Variable Selection ◽  
Joint Models ◽  
Longitudinal And Survival Data ◽  
Variable Selection And Estimation

Variable selection for joint models with time-varying coefficients

2019 ◽  
Vol 29 (1) ◽  
pp. 309-322
Author(s):  
Yujing Xie ◽  
Zangdong He ◽  
Wanzhu Tu ◽  
Zhangsheng Yu
Keyword(s):  
Variable Selection ◽  
Survival Data ◽  
Biliary Cirrhosis ◽  
Time Varying ◽  
Joint Models ◽  
Closed Form Solutions ◽  
Varying Coefficients ◽  
Shared Random Effects ◽  
Time Varying Coefficients ◽  
Time Invariant

Many clinical studies collect longitudinal and survival data concurrently. Joint models combining these two types of outcomes through shared random effects are frequently used in practical data analysis. The standard joint models assume that the coefficients for the longitudinal and survival components are time-invariant. In many applications, the assumption is overly restrictive. In this research, we extend the standard joint model to include time-varying coefficients, in both longitudinal and survival components, and we present a data-driven method for variable selection. Specifically, we use a B-spline decomposition and penalized likelihood with adaptive group LASSO to select the relevant independent variables and to distinguish the time-varying and time-invariant effects for the two model components. We use Gaussian-Legendre and Gaussian-Hermite quadratures to approximate the integrals in the absence of closed-form solutions. Simulation studies show good selection and estimation performance. Finally, we use the proposed procedure to analyze data generated by a study of primary biliary cirrhosis.

scholarly journals Improved dynamic predictions from joint models of longitudinal and survival data with time-varying effects using P-splines

Biometrics ◽  
2017 ◽  
Vol 74 (2) ◽  
pp. 685-693 ◽  
Author(s):  
Eleni-Rosalina Andrinopoulou ◽  
Paul H. C. Eilers ◽  
Johanna J. M. Takkenberg ◽  
Dimitris Rizopoulos
Keyword(s):  
Survival Data ◽  
Time Varying ◽  
Joint Models ◽  
Longitudinal And Survival Data

scholarly journals A Two-Stage Approach for Bayesian Joint Models of Longitudinal and Survival Data: Correcting Bias with Informative Prior

Entropy ◽  
2020 ◽  
Vol 23 (1) ◽  
pp. 50
Author(s):  
Valeria Leiva-Yamaguchi ◽  
Danilo Alvares
Keyword(s):  
Survival Data ◽  
Cox Model ◽  
Sensitivity Analyses ◽  
Simulation Studies ◽  
Joint Models ◽  
Two Stage ◽  
Informative Prior ◽  
Common Term ◽  
Shared Information ◽  
Longitudinal And Survival Data

Joint models of longitudinal and survival outcomes have gained much popularity in recent years, both in applications and in methodological development. This type of modelling is usually characterised by two submodels, one longitudinal (e.g., mixed-effects model) and one survival (e.g., Cox model), which are connected by some common term. Naturally, sharing information makes the inferential process highly time-consuming. In particular, the Bayesian framework requires even more time for Markov chains to reach stationarity. Hence, in order to reduce the modelling complexity while maintaining the accuracy of the estimates, we propose a two-stage strategy that first fits the longitudinal submodel and then plug the shared information into the survival submodel. Unlike a standard two-stage approach, we apply a correction by incorporating an individual and multiplicative fixed-effect with informative prior into the survival submodel. Based on simulation studies and sensitivity analyses, we empirically compare our proposal with joint specification and standard two-stage approaches. The results show that our methodology is very promising, since it reduces the estimation bias compared to the other two-stage method and requires less processing time than the joint specification approach.

scholarly journals Complete Case versus Inverse Probability Weighting Methods of Fitting Incomplete Longitudinal and Survival Data Joint Models

2019 ◽  
pp. 1-10
Author(s):  
D. O. Nyaboga ◽  
A. Mwangi ◽  
D. Lusweti
Keyword(s):  
Missing Data ◽  
Survival Data ◽  
Joint Model ◽  
Information Criteria ◽  
Joint Models ◽  
Full Data ◽  
Complete Case ◽  
Inverse Probability ◽  
Longitudinal And Survival Data ◽  
The Impact

Missing data is a common problem in real word studies especially clinical studies. However, most people working with such data, often drop missing cases from individuals with incomplete observations that occur when patients do not complete the treatment or miss their scheduled visits. This may lead to misleading results and ultimately affect the decision of whether an intervention is good or bad for the patients under treatment. The comparison of Complete Case (CC) and Inverse Probability Weights (IPW) techniques of handling missing data in various models has been addressed, however little has been done to compare these methods when applied to joint models of longitudinal and time to event data. Therefore, this paper seeks to investigate the impact of assuming CC analysis on clinical data with missing cases, comparing it with IPW method when fitting joint models of longitudinal and survival data setting full data model as the baseline model. This paper made use of randomized aids clinical trial data. The model with Deviance Information Criteria (DIC) close to that of full data joint model is considered the best. From the results, joint models from full data, CC and IPW had DIC of 10603.94, 8410.33 and 10600.95 respectively. The joint model obtained from IPW data had a DIC too close to that of full data joint model as compared to model from CC data.

Sign in / Sign up

Export Citation Format

Share Document