Many longitudinal studies (e.g. observational studies and randomized clinical trials) have collected multiple rating scales at each visit in the form of patient-reported outcomes (PROs) in the close unit interval [0,1]. We propose a joint modeling framework to address the issues from the following data features: (1) multiple correlated PROs; (2) the presence of the boundary values of zeros and ones; (3) extreme outliers and heavy tails; (4) the PRO-dependent terminal events such as death and dropout. Our modeling framework consists of a multivariate augmented mixed-effects sub-model based on Beta rectangular distributions for the multiple longitudinal outcomes and a Cox model for the terminal events. The simulation studies suggest that in the presence of outliers, heavy tails, and dependent terminal event, our proposed models provide more accurate parameter estimates than the joint model based on Beta distributions. The proposed models are applied to the motivating Long-term Study-1 (LS-1 study, n = 1741) of Parkinson’s disease patients.
FDA et al. Guidance for industry: Patient-reported outcome measures: Use in medical product development to support labeling claims. Federal Register 2009; 74(235): 65132–65133.
2.
PetoVJenkinsonCFitzpatrickR, et al.The development and validation of a short measure of functioning and well being for individuals with Parkinson’s disease. Qual Life Res1995; 4(3): 241–248.
3.
KieschnickRMcCulloughB. Regression analysis of variates observed on (0, 1): percentages, proportions and fractions. Statist Modell2003; 3(3): 193–213.
4.
FerrariSCribari-NetoF. Beta regression for modelling rates and proportions. J Appl Statist2004; 31(7): 799–815.
5.
VerkuilenJSmithsonM. Mixed and mixture regression models for continuous bounded responses using the Beta distribution. J Educ Behav Statist2012; 37(1): 82–113.
6.
Figueroa-ZúnigaJArellano-ValleRFerrariS. Mixed beta regression: A Bayesian perspective. Computat Statist Data Anal2013; 61: 137–147.
HatfieldLBoyeMCarlinB. Joint modeling of multiple longitudinal patient-reported outcomes and survival. J Biopharm Statist2011; 21(5): 971–991.
9.
HatfieldLABoyeMEHackshawMD, et al.Multilevel Bayesian models for survival times and longitudinal patient-reported outcomes with many zeros. J Am Statist Assoc2012; 107(499): 875–885.
10.
HahnE. Mixture densities for project management activity times: A robust approach to PERT. Eur J Operat Res2008; 188(2): 450–459.
11.
GarcíaCPérezJGvan DorpJ. Modeling heavy-tailed, skewed and peaked uncertainty phenomena with bounded support. Statist Meth Applic2011; 20(4): 463–486.
12.
BayesCLBazánJLGarcíaC, et al.A new robust regression model for proportions. Bayesian Anal2012; 7(4): 841–866.
13.
HendersonRDigglePDobsonA. Joint modelling of longitudinal measurements and event time data. Biostatistics2000; 1(4): 465–480.
14.
TsiatisAADavidianM. Joint modeling of longitudinal and time-to-event data: An overview. Statistica Sinica2004; 14(3): 809–834.
15.
YuMLawNJTaylorJM, et al.Joint longitudinal-survival-cure models and their application to prostate cancer. Statistica Sinica2004; 14(3): 835–862.
16.
LuoS. Joint analysis of stochastic processes with application to smoking patterns and insomnia. Statist Med2013; 32(29): 5133–5144.
17.
HeBLuoS. Joint modeling of multivariate longitudinal measurements and survival data with applications to Parkinsons disease. Statist Meth Med Res2013. in press.
18.
LuoSSuXDeSantisS, et al.Joint model for a diagnostic test without a gold standard in the presence of a dependent terminal event. Statist Med2014; 33(15): 2554–2566.
19.
LuoS. A Bayesian approach to joint analysis of multivariate longitudinal data and parametric accelerated failure time. Statist Med2014; 33: 580–594.
20.
ElmJ, et al.Design innovations and baseline findings in a long-term Parkinson’s trial: The National Institute of Neurological Disorders and Stroke Exploratory Trials in Parkinson’s Disease Long-Term Study–1. Movement Disorders2012; 27(12): 1513–1521.
21.
LawlessJZhanM. Analysis of interval-grouped recurrent-event data using piecewise constant rate functions. Can J Statist1998; 26(4): 549–565.
22.
FengSWolfeRPortF. Frailty survival model analysis of the national deceased donor kidney transplant dataset using poisson variance structures. J Am Statist Assoc2005; 100(471): 728–735.
23.
LiuLHuangX. Joint analysis of correlated repeated measures and recurrent events processes in the presence of death, with application to a study on acquired immune deficiency syndrome. J R Statist Soc Ser C (Appl Statist)2009; 58(1): 65–81.
24.
DuaneSKennedyAPendletonB, et al.Hybrid Monte Carlo. Phys Lett B1987; 195(2): 216–222.
25.
NealR. An improved acceptance procedure for the hybrid Monte Carlo algorithm. J Computat Phys1994; 111(1): 194–203.
26.
HoffmanMGelmanA. The no-U-turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo. J Machine Learning Res2013; 1593–1623.
27.
Stan Development Team. Stan Modeling Language Users Guide and Reference Manual, Version 2.5.02014.
28.
GelmanACarlinJSternH, et al.Bayesian Data Analysis, Boca Raton, FL: CRC Press, 2013.
29.
CeleuxGForbesFRobertC, et al.Deviance information criteria for missing data models. Bayesian Anal2006; 1(4): 651–673.
30.
CarlinBLouisT. Bayesian Methods for Data Analysis, London: Chapman & Hall/CRC, 2009.
31.
KassRRafteryA. Bayes factors. J Am Statist Assoc1995; 90: 773–795.
32.
LewisSRafteryA. Estimating bayes factors via posterior simulation with the Laplace–Metropolis estimator. J Am Statist Assoc1997; 92: 648–655.
DeyDChenMChangH. Bayesian approach for nonlinear random effects models. Biometrics1997; 53(4): 1239–1252.
35.
SinhaDDeyD. Semiparametric Bayesian analysis of survival data. J Am Statist Assoc1997; 92(439): 1195–1212.
36.
GhoshPHansonT. A semiparametric Bayesian approach to multivariate longitudinal data. Austral N Z J Statist2010; 52(3): 275–288.
37.
PengFDeyD. Bayesian analysis of outlier problems using divergence measures. Can J Statist1995; 23(2): 199–213.
38.
CanchoVGDeyDKLachosVH, et al.Bayesian nonlinear regression models with scale mixtures of skew-normal distributions: estimation and case influence diagnostics. Computat Statist Data Anal2011; 55(1): 588–602.
39.
KieburtzKTilleyBCElmJJ, et al.Effect of creatine monohydrate on clinical progression in patients with Parkinson disease: A randomized clinical trial. JAMA2015; 313(6): 584–593.
40.
Martinez-MartinPKurtisMM. Health-related quality of life as an outcome variable in Parkinson’s disease. Ther Adv Neurol Disord2012; 5(2): 105–117.
41.
IbrahimJGChuHChenLM. Basic concepts and methods for joint models of longitudinal and survival data. J Clin Oncol2010; 28(16): 2796–2801.
42.
SongXDavidianMTsiatisAA. A semiparametric likelihood approach to joint modeling of longitudinal and time-to-event data. Biometrics2002; 58(4): 742–753.
43.
ZengDCaiJ. Asymptotic results for maximum likelihood estimators in joint analysis of repeated measurements and survival time. Ann Statist2005; 33(5): 2132–2163.
44.
HeagertyPJKurlandBF. Misspecified maximum likelihood estimates and generalised linear mixed models. Biometrika2001; 88(4): 973–973.
45.
DanielsMJZhaoYD. Modelling the random effects covariance matrix in longitudinal data. Statist Med2003; 22(10): 1631–1647.
46.
EscobarM. Estimating normal means with a Dirichlet process prior. J Am Statist Assoc1994; 89(425): 268–277.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
