Joint models are rich and flexible models for analyzing longitudinal data with nonignorable missing data mechanisms. This article proposes a Bayesian random-effects joint model to assess the evolution of a longitudinal process in terms of a linear mixed-effects model that accounts for heterogeneity between the subjects, serial correlation, and measurement error. Dropout is modeled in terms of a survival model with competing risks and left truncation. The model is applied to data coming from ReVaPIR, a project involving children with chronic kidney disease whose evolution is mainly assessed through longitudinal measurements of glomerular filtration rate.
SchwartzGMuñozASchneiderMet al.New equations to estimate GFR in children with CKD. J Am Soc Nephrol2009; 20: 629–637.
2.
HoggRFurthSLemleyKet al.National Kidney Foundation’s Kidney Disease Outcomes Quality Initiative clinical practice guidelines for chronic kidney disease in children and adolescents: evaluation, classification, and stratification. Pediatrics2003; 6: 1416–1421.
3.
AssadiF. The epidemic of pediatric chronic kidney disease: the danger of skepticism. J Nephropathol2012; 2: 61–64.
4.
GoAChertowGFanDet al.Chronic kidney disease and the risks of death, cardiovascular events, and hospitalization. New Engl J Med2004; 351: 1296–1305.
5.
WaradyBChadhaV. Chronic kidney disease in children: the global perspective. Pediatr Nephrol2007; 22: 1999–2009.
6.
FineR. Etiology and treatment of growth retardation in children with chronic kidney disease and end-stage renal disease: a historical perspective. Pediatr Nephrol2010; 25: 725–732.
7.
DigglePJHeagertyPJLiangKYet al.Analysis of longitudinal data, 2nd ed. New York: Oxford University Press Inc., 2002.
8.
KalbfleischJDPrenticeRL. The statistical analysis of failure time data, 2nd ed. Hoboken, NJ: Wiley, 2002.
9.
TsiatisAADavidianM. Joint modeling of longitudinal and time-to-event data: an overview. Stat Sin2004; 14: 809–834.
10.
VerbekeGDavidianM. Joint models for longitudinal data: introduction and overview, Boca Raton: Chapman and Hall, 2009, pp. 319–326.
11.
WuMCCarrollRJ. Estimation and comparison of changes in the presence of informative right censoring by modelling the censoring processor. Biometrics1988; 44: 175–188.
12.
WulfsohnMSTsiatisAA. A joint model for survival and longitudinal data measured with error. Biometrics1997; 53: 330–339.
13.
HendersonRDigglePJDobsonA. Joint modelling of longitudinal measurements and event time data. Biostatistics2000; 4: 465–480.
14.
KleinJPMoeschbergerML. Survival analysis. Techniques for censored and truncated data, 2nd ed. New York: Springer-Verlag, 2003.
15.
PepeMSMoriM. Kaplan–Meier, marginal, or conditional probability curves in summarizing competing risks failure time data?Stat Med1993; 12: 737–751.
16.
PutterHFioccoMGeskusRB. Tutorial in biostatistics: competing risks and multi-state models. Stat Med2007; 26: 2389–2430.
17.
AllignolASchumacherMBeyersmannJ. Empirical transition matrix of multistate models: the etm package. J Stat Softw2011; 38: 1–15.
18.
Philipson P, Sousa I, Diggle P, et al. Package joineR. Joint modelling of repeated measurements and time-to-event data. Version 1.0-3, 2013.
19.
CressieN. Statistics for spatial data, New York: Wiley, 1991.
20.
Jacqmin-GaddaHCommengesDDartiguesJF. Random changepoint model for joint modeling of cognitive decline and dementia. Biometrics2006; 62: 254–260.
21.
ElashoffRLiGLiN. A joint model for longitudinal measurements and survival data in the presence of multiple failure types. Biometrics2008; 64: 762–771.
22.
WilliamsonPKolamunnage-DonaRPhilipsonPet al.Joint modelling of longitudinal and competing risks data. Stat Med2008; 27: 6426–6438.
23.
LiNElashoffRMLiGet al.Joint modeling of longitudinal ordinal data and competing risks survival times and analysis of the NINDS rt-PA stroke trial. Stat Med2010; 29: 546–557.
24.
AndrinopoulouERRizopoulosDTakkenbergJJMet al.Joint modeling of two longitudinal outcomes and competing risk data. Stat Med2014; 33: 3167–3178.
25.
LuT. Bayesian nonparametric mixed-effects joint model for longitudinal-competing risks data analysis in presence of multiple data features. Stat Meth Med Res2017; 26: 2407–2423.
26.
AalenOOBorganØGjessingHK. Survival and event history analysis, New York: Springer, 2008.
27.
UzunogullariUWangJL. A comparison of hazard rate estimators for left truncated and right censored data. Biometrika1992; 79: 297–310.
28.
GuoXCarlinBP. Separate and joint modeling of longitudinal and event time data using standard computer packages. Am Stat2004; 58: 1–9.
29.
Plummer M. JAGS: a program for analysis of Bayesian graphical models using Gibbs sampling. In: Proceedings of the third international workshop on distributed statistical computing, Vienna, Austria, 20–22 March 2003.
30.
GelmanARubinDB. Inference from iterative simulation using multiple sequences. Stat Sci1992; 7: 457–472.
31.
HildebrandFB. Introduction to numerical analysis, New York: Dover, 1987.
32.
WangYTaylorJMG. Jointly modeling longitudinal and event time data with application to acquired immunodeficiency syndrome. J Am Stat Assoc2001; 455: 895–905.
33.
VerbekeGSpiessensBLesaffreE. Conditional linear mixed models. Am Stat2001; 55: 25–34.
34.
Del MoralPDoucetAJasraA. Sequential Monte Carlo samplers. J R Stat Soc B2006; 68: 411–436.
35.
DoucetAJohansenA. A tutorial on particle filtering and smoothing: fifteen years later, Oxford: University of Chicago Press, 2009.
36.
AndrieuCDoucetAHolensteinR. Particle Markov chain Monte Carlo methods. J R Stat Soc Ser B (Stat Methodol)2010; 72: 269–342.
37.
RizopoulosD. Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data. Biometrics2011; 67: 819–829.
38.
TaylorJMGParkYAnkerstDPet al.Real-time individual predictions of prostate cancer recurrence using joint models. Biometrics2013; 69: 206–213.
39.
BoxG. Sampling and Bayes inference in scientific modeling and robustness (with discussion). J R Stat Assoc A1980; 143: 382–430.
40.
NtzoufrasI. Bayesian modeling using WinBUGS, Hoboken: Wiley, 2009.
41.
MarshallECSpiegelhalterDJ. Identifying outliers in Bayesian hierarchical models: a simulation-based approach. Bayesian Anal2007; 2: 409–444.
42.
BayarriMBergerJ. P-values for composite null models (with discussion). J Am Stat Assoc2000; 95: 1127–1142. 1157–1170.
43.
LangeNCarlinBPGelfandAE. Hierarchical Bayes models for the progression of HIV infection using longitudinal CD4 T-cell numbers. J Am Stat Assoc1992; 87: 325–626.
44.
RabinerLJuangB. An introduction to hidden Markov models. IEEE ASSP Magazine1986; 3: 4–16.
45.
Frühwirth-SnatterS. Finite mixture and Markov switching models, New York: Springer, 2006.
