Transformation latent variable models are proposed in this study to analyze multivariate censored data. The proposed models generalize conventional linear transformation models to semiparametric transformation models that accommodate latent variables. The characteristics of the latent variables were assessed based on several correlated observed indicators through measurement equations. A Bayesian approach was developed with Bayesian P-splines technique and the Markov chain Monte Carlo algorithm to estimate the unknown parameters and transformation functions. Simulation shows that the performance of the proposed methodology is satisfactory. The proposed method was applied to analyze a cardiovascular disease data set.
CoxDR. Regression models and life-tables (with Discussion). J Roy Stat Soc Ser B1972; 34: 187–220.
2.
ChengSCWeiLJYingZ. Analysis of transformation models with censored data. Biometrika1995; 82: 835–845.
3.
ChengSCWeiLJYingZ. Prediction of survival probabilities with semiparametric transformation models. J Am Stat Assoc1997; 92: 227–235.
4.
FineJPYingZWeiLG. On the linear transformation model for censored data. Biometrika1998; 85: 980–986.
5.
CaiTWeiLJWilcoxM. Semiparametric regression analysis for clustered failure time data. Biometrika2000; 87: 867–878.
6.
ChenKJinZYingZ. Semiparametric analysis of transformation models with censored data. Biometrika2002; 89: 659–668.
7.
PrenticeRLCaiJ. Covariance and survivor function estimation using censored multivariate failure time data. Biometrika1992; 79: 495–512.
8.
LinDY. Cox regression analysis of multivariate failure time data: The marginal approach. Stat Med1994; 13: 2233–2247.
9.
PanWLouisTA. A linear mixed-effects model for multivariate censored data. Biometrics2000; 56: 160–166.
10.
YuZLinX. Nonparametric regression using local kernel estimating equations for correlated failure time data. Biometrika2008; 95: 123–137.
11.
ChenYChenKYingZ. Analysis of multivariate failure time data using marginal proportional hazards model. Stat Sin2010; 20: 1025–1041.
12.
CaiJFanJJiangJ. Partially linear hazard regression for multivariate survival data. J Am Stat Assoc2007; 102: 538–551.
13.
BollenKA. Structural equations with latent variables, New York: Wiley, 1989.
14.
LeeSY. Structural equation modeling: A Bayesian approach, Chichester: Wiley, 2007.
15.
SongXYLeeSY. Basic and advanced Bayesian structural equation modeling: With applications in the medical and behavioral sciences, Chichester: John Wiley & Sons, Ltd, 2012.
16.
TzalaEBestN. Bayesian latent variable modelling of multivariate spatio-temporal variation in cancer mortality. Stat Methods Med Res2008; 17: 97–118.
17.
ChoiJLawsonABCaiB. A Bayesian latent model with spatio-temporally varying coefficients in low birth weight incidence data. Stat Methods Med Res2012; 21: 445–456.
18.
LukAOSoWYMaRC. Metabolic syndrome predicts new onset of chronic kidney disease in 5,829 patients with Type 2 diabetes: A 5-year prospective analysis of the Hong Kong Diabetes Registry. Diabetes Care2008; 31: 2357–2361.
19.
DunsonDB. Bayesian latent variable models for clustered mixed outcomes. J Roy Stat Soc Ser B2000; 62: 355–366.
20.
DunsonDBPerreaultSD. Factor analytic models of clustered multivariate data with informative censoring. Biometrics2001; 57: 302–308.
21.
DunsonDBDinseGE. Bayesian models for multivariate current status data with informative censoring. Biometrics2002; 58: 79–88.
CongdonP. Bayesian statistical modelling, New York: John Wiley & Sons, 2006.
24.
ScheinesRHoijtinkHBoomsmaA. Bayesian estimation and testing of structural equation models. Psychometrika1999; 64: 37–52.
25.
GemanSGemanD. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans Pattern Anal Mach Intell1984; 6: 721–741.
26.
MetropolisNRosenbluthAWRosenbluthMN. Equation of state calculations by fast computing machines. J Chem Phys1953; 21: 1087–1091.
27.
HastingsWK. Monte Carlo sampling methods using Markov chains and their applications. Biometrika1970; 57: 97–109.
28.
BoxGEPCoxDR. An analysis of transformations. J Roy Stat Soc Ser B1964; 26: 211–252.
29.
SammelMDRyanLM. Latent variable models with fixed effects. Biometrics1996; 52: 650–663.
30.
RoyJLinX. Latent variable models for longitudinal data with multiple continuous outcomes. Biometrics2000; 56: 1047–1054.
31.
RoyJLinX. Analysis of multivariate longitudinal outcomes with nonignorable dropouts and missing covariates: Changes in methadone treatment practices. J Am Stat Assoc2002; 97: 40–52.
32.
GreenPJSilvermanBW. Nonparametric regression and generalized linear models: A roughness penalty approach, London: Chapman & Hall, 1993.
33.
FanJGijbelsI. Local polynomial modelling and its applications, London: Chapman & Hall, 1996.
34.
RuppertDWandMPCarrollRJ. Semiparametric regression, Cambridge: Cambridge University Press, 2003.
35.
BerrySMCarrollRJRuppertD. Bayesian smoothing and regression splines for measurement error problems. J Am Stat Assoc2002; 97: 160–169.
36.
FahrmeirLRaachA. A Bayesian semiparametric latent variable model for mixed responses. Psychometrika2007; 72: 327–346.
EilersPHCMarxBD. Flexible smoothing with B–splines and penalties. Stat Sci1996; 11: 89–121.
42.
TannerMAWongWH. The calculation of posterior distributions by data augmentation (with discussion). J Am Stat Assoc1987; 82: 528–550.
43.
ChanJCMalikVJiaW. Diabetes in Asia: Epidemiology, risk factors, and pathophysiology. J Am Med Assoc2009; 301: 2129–2140.
44.
ChanJCSoWMaRC. The complexity of vascular and non-vascular complications of diabetes: The Hong Kong Diabetes Registry. Curr Cardiovasc Risk Rep2011; 5: 230–239.
45.
SongXYLeeSYMaRC. Phenotype-genotype interactions on renal function in type 2 diabetes: An analysis using structural equation modelling. Diabetologia2009; 52: 1543–1553.
46.
SongXYLeeSYNgMC. Bayesian analysis of structural equation models with multinomial variables and an application to type 2 diabetic nephropathy. Stat Med2007; 26: 2348–2369.
47.
LeeSYSongXY. Evaluation of the Bayesian and maximum likelihood approaches in analyzing structural equation models with small sample sizes. Multivar Behav Res2004; 39: 653–686.
48.
GelmanARobertsGOGilksWREfficient metropolis jumping rules. In: BernardoJMBergerJODawidAP (eds). Bayesian statistics 5, New York: Oxford University Press, 1996, pp. 599–607.
49.
LiuJSLiangFWongWH. The multiple-try method and local optimization in metropolis sampling. J Am Stat Assoc2000; 95: 121–134.
50.
ChenMHSchmeiserB. Performance of the Gibbs, Hit-and-Run, and Metropolis samplers. J Comput Graph Stat1993; 2: 251–272.
