×

Joint modeling of cross-sectional health outcomes and longitudinal predictors via mixtures of means and variances. (English) Zbl 1390.62274

Summary: Joint modeling methods have become popular tools to link important features extracted from longitudinal data to a primary event. While most modeling strategies have focused on the association between the longitudinal mean trajectories and risk of an event, we consider joint models that incorporate information from both long-term trends and short-term variability in a longitudinal submodel. We also consider both shared random effect and latent class (LC) approaches in the primary-outcome model to predict a binary outcome of interest. We develop simulation studies to compare and contrast these two modeling strategies; in particular, we study in detail the effects of the primary-outcome model misspecification. Among other findings, we note that when we analyze data from a shared random-effect using a LC model while the information from the longitudinal data is weak, the LC approach is more sensitive to such a model misspecification. Under this setting, the LC model has a superior performance in within-sample prediction that cannot be duplicated when predicting new samples. This is a unique feature of the LC approach that is new as far as we know to the existing literature. Finally, we use the proposed models to study how follicle stimulating hormone (FSH) trajectories are related to the risk of developing severe hot flashes for participating women in the Penn Ovarian Aging Study.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62J15 Paired and multiple comparisons; multiple testing
62H20 Measures of association (correlation, canonical correlation, etc.)

Software:

ROCR
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Albert, Bayesian analysis of binary and polychotomous response data, Journal of the American Statistical Association 88 pp 669– (1993) · Zbl 0774.62031 · doi:10.1080/01621459.1993.10476321
[2] Brier, Verification of forecasts expressed in terms of probability, Monthly Weather Review 78 pp 1– (1950) · doi:10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2
[3] Celeux, Deviance information criteria for missing data models, Bayesian Analysis 1 pp 651– (2006) · Zbl 1331.62329 · doi:10.1214/06-BA122
[4] Day, Estimating the components of a mixture of normal distributions, Biometrika 56 pp 463– (1969) · Zbl 0183.48106 · doi:10.1093/biomet/56.3.463
[5] Elliott, Identifying latent clusters of variability in longitudinal data, Biostatistics 8 pp 756– (2007) · Zbl 1267.62058 · doi:10.1093/biostatistics/kxm003
[6] Elliott, Using a Bayesian latent growth curve model to identify trajectories of positive affect and negative events following myocardial infarction, Biostatistics 6 pp 119– (2005) · Zbl 1069.62095 · doi:10.1093/biostatistics/kxh022
[7] Elliott, Associations between variability of risk factors and health outcomes in longitudinal studies, Statistics in Medicine 31 pp 2745– (2012) · doi:10.1002/sim.5370
[8] Fawcett, An introduction to ROC analysis, Pattern Recognition Letters 27 pp 861– (2006) · doi:10.1016/j.patrec.2005.10.010
[9] Freeman, Duration of menopausal hot flushes and associated risk factors, Obstetrics and Gynecology 117 pp 1095– (2011) · doi:10.1097/AOG.0b013e318214f0de
[10] Freeman, Associations of hormones and menopausal status with depressed mood in women with no history of depression, Archives of General Psychiatry 63 pp 375– (2006) · doi:10.1001/archpsyc.63.4.375
[11] Frühwirth-Schnatter, Finite Mixture and Markov Switching Models (2006)
[12] Garrett, Latent class model diagnosis, Biometrics 56 pp 1055– (2000) · Zbl 1116.62428 · doi:10.1111/j.0006-341X.2000.01055.x
[13] Geisser, A predictive approach to model selection, Journal of the American Statistical Association 74 pp 153– (1979) · Zbl 0401.62036 · doi:10.1080/01621459.1979.10481632
[14] Gelman, Bayesian Data Analysis (2003) · Zbl 1114.62320
[15] Henderson, Joint modeling of longitudinal measurements and event time data, Biostatistics 1 pp 465– (2000) · Zbl 1089.62519 · doi:10.1093/biostatistics/1.4.465
[16] Ibrahim, Bayesian survival analysis (2001) · Zbl 0978.62091 · doi:10.1007/978-1-4757-3447-8
[17] Ibrahim, Basic concepts and methods for joint models of longitudinal and survival data, Journal of Clinical Oncology 28 pp 2796– (2010) · doi:10.1200/JCO.2009.25.0654
[18] Kass, A default conjugate prior for variance components in generalized linear mixed models (comment on article by Browne and Draper), Bayesian Analysis 1 pp 535– (2006) · Zbl 1331.62148 · doi:10.1214/06-BA117B
[19] McLachlan, Finite Mixture Models (2000) · Zbl 0963.62061 · doi:10.1002/0471721182
[20] Muthén, Finite mixture modeling with mixture outcomes using the EM algorithm, Biometrics 55 pp 463– (1999) · Zbl 1059.62599 · doi:10.1111/j.0006-341X.1999.00463.x
[21] Proust-Lima, Joint latent class models for longitudinal and time-to-event data: A review, Statistical Methods in Medical Research (2012)
[22] Redner, Mixture densities, maximum likelihood and the em algorithm, SIAM Review 26 pp 195– (1984) · Zbl 0536.62021 · doi:10.1137/1026034
[23] Sammel, Proceedings of the Joint Meeting of the American Statistical Association (2001)
[24] Sing, ROCR: Visualizing classifier performance in R, Bioinformatics 21 pp 3940– (2005) · doi:10.1093/bioinformatics/bti623
[25] Spiegelhalter, Measures of model complexity and fit, Journal of the Royal Statistical Society, Series B (Statistical Methodology) 64 pp 583– (2002) · Zbl 1067.62010 · doi:10.1111/1467-9868.00353
[26] Stephens, Dealing with label switching in mixture models, Journal of the Royal Statistical Society, Series B (Statistical Methodology) 62 pp 795– (2000) · Zbl 0957.62020 · doi:10.1111/1467-9868.00265
[27] Tsiatis, Joint modeling of longitudinal and time-to-event data: An overview, Statistica Sinica 14 pp 809– (2004) · Zbl 1073.62087
[28] Verbeke, A linear mixed-effects model with heterogeneity in the random-effects population, Journal of the American Statistical Association 91 pp 217– (1996) · Zbl 0870.62057 · doi:10.1080/01621459.1996.10476679
[29] Wu, Estimation and comparison of changes in the precence of informative right censoring by modeling the censoring process, Biometrics 44 pp 175– (1988) · Zbl 0707.62210 · doi:10.2307/2531905
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.