Skip to main content

Table 1 Summary of longitudinal sub-models with single longitudinal outcome

From: Bayesian joint modelling of longitudinal and time to event data: a methodological review

 Number of articles (%)Reference
Type of outcome
 Continuous39(95.1%)[13, 15,16,17,18,19, 22,23,24,25, 27, 33, 35, 37,38,39,40, 43, 44, 46,47,48, 51, 52, 55, 56, 59,60,61,62, 65, 66, 75,76,77,78,79,80,81]
 Count2(4.9%)[31, 53]
Model
 GLM, NLME, SNLME, Semiparametric random-effects modela5(12.2%)[51, 52, 77, 78, 81]
 LME13(31.7%)[15,16,17,18,19, 23, 33, 35, 46, 48, 62, 75, 76]
 Partially LME4(9.8%)[22, 37, 56, 61]
 Mixed effect model, Mixed effect model with IOU stochastic process, Mixed-effect varying coefficient Tobit model, Bent-cable mixed-effects modela4(9.8%)[25, 39, 44, 47]
 Mixed-effects varying-coefficient model3(7.3%)[27, 38, 80]
 LQMM, Quantile-based mixed model, QR- NLME, QR-NLMETa4(9.8%)[24, 59, 60, 79]
 Hurdle two-part model and Longitudinal Tobit modela2(4.8%)[43, 66]
 Random change point model, Multiple-change point model, Longitudinal model for the immune response a4(9.8%)[13, 40, 55, 65]
 ZAB, Two zero-inflated count modelsa2(4.8%)[31, 53]
Random effect distribution
 Normal17(47.4%)[13, 15, 19, 25, 27, 33, 38, 46, 47, 51, 55, 60, 75,76,77, 79,80,81]
 Multivariate normal10(26.3%)[16,17,18, 24, 39, 43, 44, 59, 62, 66]
 Finite mixture of normal distributions, N/Ia3(7.9%)[48], [23, 35]
 Dirichlet process prior2(5.3%)[40, 52]
 Spline5(13.1%)[22, 37, 56, 61, 78]
Error distribution
 Normal18(48.6%)[13, 16, 17, 19, 33, 39, 40, 46,47,48, 52, 55, 62, 65, 66, 75, 76, 81]
 N/I, SNa3(8.1%)[23, 35], [51]
 t-distribution1(2.8%)[18]
 ST6(16.2%)[15, 22, 37, 38, 56, 61]
 Multivariate ST6(16.2%)[25, 27, 44, 77, 78, 80]
 ALD3(8.1%)[24, 59, 79]
  1. aThe order of the outcomes/models/distributions have the same order as in the reference