×

Robust joint modeling of longitudinal measurements and time to event data using normal/independent distributions: a Bayesian approach. (English) Zbl 1441.62280

Summary: Joint modeling of longitudinal data and survival data has been used widely for analyzing AIDS clinical trials, where a biological marker such as CD4 count measurement can be an important predictor of survival. In most of these studies, a normal distribution is used for modeling longitudinal responses, which leads to vulnerable inference in the presence of outliers in longitudinal measurements. Powerful distributions for robust analysis are normal/independent distributions, which include univariate and multivariate versions of the Student’s t, the slash and the contaminated normal distributions in addition to the normal. In this paper, a linear-mixed effects model with normal/independent distribution for both random effects and residuals and Cox’s model for survival time are used. For estimation, a Bayesian approach using Markov Chain Monte Carlo is adopted. Some simulation studies are performed for illustration of the proposed method. Also, the method is illustrated on a real AIDS data set and the best model is selected using some criteria.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62F15 Bayesian inference

Software:

boa; WinBUGS
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Acuna , E. Rodriguez , C. A. 2004 http://academic.uprm.edueacuna/paperout.pdf
[2] Andrews, Scale mixtures of normal distributions, Journal of the Royal Statistical Society-Series B 36 pp 99– (1974) · Zbl 0282.62017
[3] Chen, A new joint model for longitudinal and survival data with a cure fraction, Journal of Multivariate Analysis 91 pp 18– (2004) · Zbl 1051.62098 · doi:10.1016/j.jmva.2004.04.005
[4] Chi, Joint models for multivariate longitudinal and multivariate survival data, Biometrics 62 pp 432– (2006) · Zbl 1097.62122 · doi:10.1111/j.1541-0420.2005.00448.x
[5] Christensen, Bayesian Ideas and Data Analysis, An Introduction for Scientists and Statisticians (2011)
[6] Diggle, Informative dropout in longitudinal data analysis (with discussion), Journal of the Royal Statistical Society, Series C: Applied Statistics 43 pp 49– (1994) · Zbl 0825.62010
[7] Efron, The geometry of exponential families, In Annals of Statistics 6 pp 362– (1978) · Zbl 0436.62027 · doi:10.1214/aos/1176344130
[8] Fahrmeir, Bayesian regularization in structured additive regression: a unifying perspective on shrinkage, smoothing and predictor selection, Statistics and computing 20 pp 203– (2010) · doi:10.1007/s11222-009-9158-3
[9] Gelfand, Bayesian model choice: asymptotics and exact calculations, Journal of the Royal Statistical Society Series B 56 pp 501– (1994) · Zbl 0800.62170
[10] Gelman, Inference from iterative simulation using multiple sequences, Statistical Science 7 pp 457– (1992) · Zbl 1386.65060 · doi:10.1214/ss/1177011136
[11] Geweke, Bayesian Statistics (1992)
[12] Geweke, Bayesian treatment of the independent Student-t linear model, Journal of Applied Economic 8 pp 19– (1993) · doi:10.1002/jae.3950080504
[13] Goldman, Response of CD4+ and clinical consequences to treatment using ddI or ddC in patients with advanced HIV infection, Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology 11 pp 161– (1996) · doi:10.1097/00042560-199602010-00007
[14] Guo, Separate and joint modeling of longitudinal and event time data using standard computer packages, The American Statistician 58 (9) pp 16– (2004) · Zbl 05680562 · doi:10.1198/0003130042854
[15] Hashemi, A latent process model for joint modeling of events and markers, Lifetime Data Analysis 8 pp 335– (2003) · Zbl 1116.62430 · doi:10.1023/A:1020514804325
[16] Heidelberger, Simulation run length control in the presence of an initial transient, Operations Research 31 pp 1109– (1983) · Zbl 0532.65097 · doi:10.1287/opre.31.6.1109
[17] Henderson, Joint modeling of longitudinal measurements and event time data, Biostatistics 4 pp 465– (2000) · Zbl 1089.62519 · doi:10.1093/biostatistics/1.4.465
[18] Hogan, Model-based approaches to analysing incomplete longitudinal and failure time data, Statistics in Medicine 16 pp 259– (1997) · doi:10.1002/(SICI)1097-0258(19970215)16:3<259::AID-SIM484>3.0.CO;2-S
[19] Huang, A joint model of longitudinal and competing risks survival data with heterogeneous random effects and outlying longitudinal, Statistics Interface 3 pp 185– (2010) · Zbl 1245.62124 · doi:10.4310/SII.2010.v3.n2.a6
[20] Ibrahim, Bayesian Survival Analysis (2002)
[21] Ibrahim, Bayesian methods for joint modeling of longitudinal and survival data with application to cancer vaccine trials, Statistica Sinica 14 pp 863– (2004) · Zbl 1073.62100
[22] Iglewics, Outlier Detection using robust measures of scale, Journal of Sattistical Computation and Simulation 15 pp 285– (1982) · doi:10.1080/00949658208810595
[23] Kalbfleisch, The Statistical Analysis of Failure Time Data (2002) · Zbl 1012.62104 · doi:10.1002/9781118032985
[24] Kotz, Continuous multivariate distributions : Models and Applications (2000) · Zbl 0946.62001 · doi:10.1002/0471722065
[25] Kotz, Multivariate T-Distributions and Their Applications (2004) · Zbl 1100.62059 · doi:10.1017/CBO9780511550683
[26] Lange, Robust statistical modeling using the t distribution, Journal of the American Statistical Association 84 pp 881– (1989)
[27] Lange, Normal/independent distributions and their applications in robust regression, Journal of the American Statistical Association 2 pp 175– (1993)
[28] Li, Robust joint modeling of longitudinal measurements and competing risks failure time data, Biometrics 51 pp 19– (2009) · doi:10.1002/bimj.200810491
[29] Little, Robust estimation of the mean and covariance matrix from data with missing values, Applied Statistics 37 pp 23– (1988) · Zbl 0647.62040 · doi:10.2307/2347491
[30] Ohlssen, Flexible random-effects models using Bayesian semi-parametric models: applications in institutional comparisons, Statistics in Medicine 26 pp 2088– (2007) · doi:10.1002/sim.2666
[31] Pinheiro, Efficient algorithms for robust estimation in linear mixed-effects models using the multivariate t distribution, Journal of Computational and Graphical Statistics 10 pp 249– (2001) · Zbl 04567023 · doi:10.1198/10618600152628059
[32] Rosa, Robust linear mixed models with normal/independent distributions and Bayesian MCMC implementation, Biometrical Journal 45 pp 573– (2003) · doi:10.1002/bimj.200390034
[33] Smith, boa: an R package for MCMC output convergence assessment and posterior inference, Journal of Statistical Software 21 pp 1– (2007) · doi:10.18637/jss.v021.i11
[34] Spiegelhalter, Bayesian measures of model complexity and fit, Journal of the Royal Statistical Society Series B 64 pp 583– (2002) · Zbl 1067.62010 · doi:10.1111/1467-9868.00353
[35] Spiegelhalter , D. J. Thomas , A. Best , N. Lunn , D. 2003 WinBUGS Examples, MRC Biostatistics Unit, Institute of Public Health and Department of Epidemiology and Public Health, Imperial College School of Medicine, UK Available at http://www.mrc-bsu.cam.ac.uk/bugs
[36] Taylor, Real-time individual predictions of prostate cancer recurrence using joint models, Biometrics (2012)
[37] Tseng, Joint modelling of accelerated failure time and longitudinal data, Biometrika 92 pp 587– (2005) · Zbl 1152.62380 · doi:10.1093/biomet/92.3.587
[38] Tsiatis, A semiparametric estimator for the proportional hazards model with longitudinal covariates measured with error, Biometrika 88 pp 447– (2001) · Zbl 0984.62078 · doi:10.1093/biomet/88.2.447
[39] Tukey, Contributions to Probability and Statistics pp 448– (1960)
[40] Wang, The multivariate skew-slash distribution, Journal of Statistical Planning and Inference 136 pp 209– (2006) · Zbl 1081.60013 · doi:10.1016/j.jspi.2004.06.023
[41] Wu, Mixed Effects Models for Complex Data (2010) · Zbl 1268.62067
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.