×

Bayesian two-component measurement error modelling for survival analysis using INLA – a case study on cardiovascular disease mortality in Switzerland. (English) Zbl 1464.62135

Summary: Measurement error (ME) in explanatory variables is a common problem in regression and survival analysis, as it may cause bias in the estimated parameters. It is shown how the integrated nested Laplace approximations (INLA) method can handle classical and Berkson ME in a single explanatory variable, illustrated for the case of a Weibull regression model. To this end, a two-component error model to account for a mix of Berkson and classical ME in a single covariate is introduced and applied to a study on cardiovascular disease (CVD) mortality in Switzerland. In particular, the model was used to correct for error in the self-reported mean daily number of cigarettes smoked, as well as in reportings of systolic blood pressure (SBP). Both variables suffer from classical error induced by an imprecision, either due to misremembering of study participants (cigarettes), or due to practical difficulties in obtaining accurate measurements (SBP), but also from a Berkson-type error that is induced by a rounding behaviour, also known as digit preference. In both cases, the effect estimates increased when the error was taken into account. Therefore, an important conclusion is that ME modelling in survival analysis is relevant, and a ready-to-use Bayesian solution including -code is provided.

MSC:

62-08 Computational methods for problems pertaining to statistics
62P10 Applications of statistics to biology and medical sciences; meta analysis

Software:

JAGS; R; BUGS; survival
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Augustin, T., An exact corrected log-likelihood function for cox’s proportional hazards model under measurement error and some extensions, Scand. J. Statist., 31, 43-50, (2004) · Zbl 1053.62108
[2] Augustin, T.; Schwarz, R., Cox’s proportional hazards model under covariate measurement error: A review and comparison of methods, (Van Huffel, S.; Lemmerling, P., Total Least Squares and Error-in-Variables Modelling: Analysis, Algorithms and Applications, (2002), Springer Netherlands), 175-188 · Zbl 0989.62052
[3] Berkson, J., Are there two regressions?, J. Amer. Statist. Assoc., 45, 164-180, (1950) · Zbl 0040.22404
[4] Bopp, M.; Braun, J.; Gutzwiller, F.; Faeh, D., Health risk or resource? gradual and independent association between self-rated health and mortality persists over 30 years, PLoS One, 7, e30795, (2012), for the Swiss National Cohort Study Group
[5] Camarda, C. G.; Eilers, P. H.C.; Gampe, J., Modelling general patterns of digit preference, Stat. Model., 8, 385-401, (2008)
[6] Carroll, K. J., On the use and utility of the Weibull model in the analysis of survival data, Controlled Clin. Trials, 24, 682-701, (2003)
[7] Carroll, R. J.; Ruppert, D.; Stefanski, L. A.; Crainiceanu, C. M., Measurement error in nonlinear models: A modern perspective, (2006), Chapman & Hall Boca Raton · Zbl 1119.62063
[8] Carroll, R. J.; Spiegelman, C. H.; Lan, K. K.G.; Bailey, K. T.; Abbott, R. D., On errors-in-variables for binary regression models, Biometrika, 71, 19-25, (1984) · Zbl 0566.62093
[9] Carroll, R. J.; Stefanski, L. A., Approximate quasilikelihood estimation in models with surrogate predictors, J. Amer. Statist. Assoc., 85, 652-663, (1990)
[10] Clayton, D., Models for the longitudinal analysis of cohort and case-control studies with inaccurately measured exposures, (Dwyer, J. H.; Feinleib, M.; Lippert, P.; Hoffmeister, H., Statistical Models for Longitudinal Studies of Health, (1992), Oxford University Press), 301-331
[11] Collett, D., (Modelling Survival Data in Medical Research, Texts in Statistical Science, (2015), Chapman & Hall/CRC Boca Raton)
[12] Cook, J. R.; Stefanski, L. A., Simulation-extrapolation estimation in parametric measurement error models, J. Amer. Statist. Assoc., 89, 1314-1328, (1994) · Zbl 0810.62028
[13] Cox, D. R., Regression models and life-tables, J. R. Stat. Soc. Ser. B Stat. Methodol., 34, 187-220, (1972) · Zbl 0243.62041
[14] Dellaportas, P.; Stephens, D. A., Analysis of errors-in-variables regression models, Biometrics, 51, 1085-1095, (1995) · Zbl 0867.62013
[15] de Lusignan, S.; Belsey, J.; Hague, N.; Dzregah, B., End-digit preference in blood pressure recordings of patients with ischaemic heart disease in primary care, J. Hum. Hypertens., 18, 261-265, (2004)
[16] Fong, Y.; Rue, H.; Wakefield, J., Bayesian inference for generalized linear mixed models, Biostatistics, 11, 397-412, (2010)
[17] Fuller, W. A., Measurement error models, (1987), John Wiley & Sons New York · Zbl 0800.62413
[18] Gimenez, P.; Bolfarine, H.; Colosimo, E. A., Estimation in Weibull regression model with measurement error, Comm. Statist. Theory Methods, 28, 495-510, (1999) · Zbl 0920.62025
[19] Gleser, L. J., Improvements of the naive approach to estimation in nonlinear errors-in-variables regression models, (Brown, P. J.; Fuller, W. A., Statistical Analysis of Measurement Error Models and Applications, (1990), American Mathematical Society), 99-114
[20] Gustafson, P., Measurement error and misclassification in statistics and epidemiology: impacts and Bayesian adjustments, (2004), Chapman & Hall/CRC Boca Raton · Zbl 1039.62019
[21] Gustafson, P., On model expansion, model contraction, identifiability and prior information: two illustrative scenarios involving mismeasured variables, Statist. Sci., 20, 111-140, (2005) · Zbl 1087.62037
[22] Gutzwiller, F.; Nater, B.; Martin, J., Community-based primary prevention of cardiovascular disease in Switzerland: methods and results of the national research program 1A (NRP1A), Prev. Med., 14, 482-491, (1985)
[23] Heid, I. M.; Küchenhoff, H.; Miles, J.; Kreienbrock, L.; Wichmann, H. E., Two dimensions of measurement error: classical and Berkson error in residential Radon exposure assessment, J. Exposure Anal. Environ. Epidemiol., 14, 365-377, (2004)
[24] Held, L., Simultaneous posterior probability statements from Monte Carlo output, J. Comput. Graph. Statist., 13, 20-35, (2004)
[25] Held, L.; Sauter, R., Adaptive prior weighting in generalized regression models, Biometrics, (2016)
[26] Hu, P.; Tsiatis, A. A.; Davidian, M., Estimating the parameters in the Cox model when covariate variables are measured with error, Biometrics, 54, 1407-1419, (1998) · Zbl 1058.62557
[27] Hughes, M. D., Regression dilution in the proportional hazards model, Biometrics, 49, 1056-1066, (1993) · Zbl 0819.62074
[28] Kalbfleisch, J. D.; Prentice, R. L., The statistical analysis of failure-time data, (2002), Wiley New York · Zbl 1012.62104
[29] Kerber, R. A.; Till, J. E.; Simon, S. L.; Lyon, J. L.; Thomas, D. C.; Preston-Martin, S.; Rallison, M. L.; Lloyd, R. D.; Stevens, W., A cohort study of thyroid disease in relation to fallout from nuclear weapons testing, J. Amer. Med. Assoc., 270, 2076-2082, (1993)
[30] Khan, T. V.; Khan, S. S.; Akhondi, A.; Khan, T. W., White coat hypertension: relevance to clinical and emergency medical services personnel, Medscape Gen. Med., 9, 52, (2007)
[31] Klesges, R.; Debon, M.; Ray, J. W., Are self-reports of smoking rate biased? evidence from the second national health and nutrition examination survey, J. Clin. Epidemiol., 48, 1225-1233, (1995)
[32] Küchenhoff, H.; Bender, R.; Langner, I., Effect of Berkson measurement error on parameter estimates in Cox regression models, Lifetime Data Anal., 13, 261-272, (2007) · Zbl 1162.62418
[33] Küchenhoff, H.; Mwalili, S. M.; Lesaffre, E., A general method for dealing with misclassification in regression: the misclassification SIMEX, Biometrics, 62, 85-96, (2006) · Zbl 1091.62057
[34] Li, Y.; Clyde, M. A., Mixtures of \(g\)-priors in generalized linear models. tech. rep., (2016), Clemson/Duke University
[35] Lindley, D. V.; El-Sayyad, G. M., The Bayesian estimation of a linear functional relationships, J. R. Stat. Soc. Ser. B Stat. Methodol., 30, 190-202, (1968) · Zbl 0155.26102
[36] Lunn, D.; Spiegelhalter, D.; Thomas, A.; Best, N., The BUGS project: evolution, critique, and future directions, Stat. Med., 28, 3049-3067, (2009)
[37] Martino, S.; Akerkar, R.; Rue, H., Approximate Bayesian inference for survival models, Scand. J. Statist., 38, 514-528, (2011) · Zbl 1246.62059
[38] Martins, T. G.; Rue, H., Extending INLA to a class of near-Gaussian latent models, Scand. J. Statist., 41, 893-912, (2014) · Zbl 1305.62268
[39] Martins, T. G.; Simpson, D.; Lindgren, F.; Rue, H., Bayesian computing with INLA: new features, Comput. Statist. Data Anal., 67, 68-83, (2013)
[40] McCrink, L., Robust joint modelling: the impact of longitudinal outliers. tech. rep., (2016), Unversity of Belfast UK, (submitted for publication)
[41] Muff, S.; Keller, L. F., Reverse attenuation in interaction terms due to covariate error, Biom. J., 6, 1068-1083, (2015) · Zbl 1386.62023
[42] Muff, S.; Riebler, A.; Held, L.; Rue, H.; Saner, P., Bayesian analysis of measurement error models using integrated nested Laplace approximations, J. R. Stat. Soc. Ser. C. Appl. Stat., 64, 231-252, (2015)
[43] Myers, R. J., Accuracy of age reporting in the 1950 united states census, J. Amer. Statist. Assoc., 49, 826-831, (1954)
[44] Nakamura, T., Corrected score functions for errors-in-variables models: methodology and application to generalized linear models, Biometrika, 77, 127-137, (1990) · Zbl 0691.62066
[45] Nakamura, T., Proportional hazards model with covariates subject to measurement error, Biometrics, 48, 829-838, (1992)
[46] Plummer, M., 2003. JAGS: A program for analysis of Bayesian graphical models using Gibbs sampling. In: Proceedings of the 3rd International Workshop on Distributed Statistical Computing.
[47] Prentice, R. L., Covariate measurement errors and parameter estimation in a failure time regression model, Biometrika, 69, 331-342, (1982) · Zbl 0523.62083
[48] Prentice, R. L.; Kalbfleisch, J. D., Hazard rate models with covariates, Biometrics, 35, 25-39, (1979) · Zbl 0414.62052
[49] R: A language and environment for statistical computing, (2016), R Foundation for Statistical Computing Vienna, Austria, URL https://www.R-project.org/
[50] Richardson, S.; Gilks, W. R., Conditional independence models for epidemiological studies with covariate measurement error, Stat. Med., 12, 1703-1722, (1993)
[51] Rudemo, M.; Ruppert, D.; Streibig, J. C., Random-effect models in nonlinear regression with applications to bioassay, Biometrics, 45, 349-362, (1989) · Zbl 0715.62253
[52] Rue, H.; Martino, S.; Chopin, N., Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion), J. R. Stat. Soc. Ser. B Stat. Methodol., 71, 319-392, (2009) · Zbl 1248.62156
[53] Sabanés Bové, D.; Held, L., Bayesian fractional polynomials, Stat. Comput., 21, 309-324, (2011) · Zbl 1255.62058
[54] Schafer, D. W., Covariate measurement error in generalized linear models, Biometrika, 74, 385-391, (1987) · Zbl 0619.62047
[55] Schafer, D. W., Likelihood analysis for probit regression with measurement errors, Biometrika, 80, 899-904, (1993) · Zbl 0800.62448
[56] Simon, S. L.; Till, J. E.; Lloyd, R. D.; Kerber, R. L.; Thomas, D. C.; Preston-Martin, S.; Lyon, J. L.; Stevens, W., The Utah leukemia case-control study: dosimetry methodology and results, Health Phys., 68, 460-471, (1995)
[57] Song, X.; Davidian, M.; Tsiatis, A. A., An estimator for the proportional hazards model with multiple longitudinal covariates measured with error, Biostatistics, 3, 511-528, (2002) · Zbl 1138.62360
[58] Stefanski, L. A., Unbiased estimation of a nonlinear function of a normal mean with application to measurement error models, Commun. Statist. Ser. A, 18, 4335-4358, (1989) · Zbl 0707.62058
[59] Stephens, D. A.; Dellaportas, P., Bayesian analysis of generalised linear models with covariate measurement error, (Bernardo, J. M.; Berger, J. O.; Dawid, A. P.; Smith, A. F.M., Bayesian Statistics 4, (1992), Oxford Univ. Press)
[60] Tadesse, M. G.; Ibrahim, J. G.; Gentleman, R.; Chiaretti, S.; Ritz, J.; Foa, R., Bayesian error-in-variable survival model for the analysis of genechip arrays, Biometrics, 61, 488-497, (2005) · Zbl 1077.62116
[61] Therneau, T., 2015. A Package for Survival Analysis in S. Version 2.38. URL http://CRAN.R-project.org/package=survival.
[62] Volinsky, C. T.; Raftery, A. E., Bayesian information criterion for censored survival models, Biometrics, 56, 256-262, (2000) · Zbl 1060.62557
[63] Von Gunten, E.; Braun, J.; Bopp, M.; Keller, U.; Faeh, D., J-shaped association between plasma glucose concentration and cardiovascular disease mortality over a follow-up of 32 years, Prev. Med., 57, 623-628, (2013)
[64] Wang, X.; George, E. I., Adaptive Bayesian criteria in variable selection for generalized linear models, Statist. Sinica, 17, 2, 667-690, (2007) · Zbl 1128.62081
[65] Wang, H.; Heitjan, D. F., Modeling heaping in self-reported cigarette counts, Stat. Med., 27, 3789-3804, (2008)
[66] Wang, H.; Shiffman, S.; Griffith, S. D.; Heitjan, D. F., Truth and memory: linking instantaneous and retrospective self-reported cigarette consumption, Ann. Appl. Stat., 6, 1689-1706, (2012) · Zbl 1257.62129
[67] Zellner, A., On assessing prior distributions and Bayesian regression analysis with \(g\)-prior distributions, (Goel, P. K.; Zellner, A., Bayesian Inference and Decision Techniques: Essays in Honor of Bruno de Finetti, Studies in Bayesian Econometrics and Statistics, vol. 6, (1986), North-Holland Amsterdam), 233-243 · Zbl 0655.62071
[68] Zelnik, M., Age heaping in the united states census: 1880-1950, Milbank Memorial Fund Q., 39, 540-573, (1961)
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.