×

Quantile regression for mixed models with an application to examine blood pressure trends in China. (English) Zbl 1454.62400

Summary: Cardiometabolic diseases have substantially increased in China in the past 20 years and blood pressure is a primary modifiable risk factor. Using data from the China Health and Nutrition Survey, we examine blood pressure trends in China from 1991 to 2009, with a concentration on age cohorts and urbanicity. Very large values of blood pressure are of interest, so we model the conditional quantile functions of systolic and diastolic blood pressure. This allows the covariate effects in the middle of the distribution to vary from those in the upper tail, the focal point of our analysis. We join the distributions of systolic and diastolic blood pressure using a copula, which permits the relationships between the covariates and the two responses to share information and enables probabilistic statements about systolic and diastolic blood pressure jointly. Our copula maintains the marginal distributions of the group quantile effects while accounting for within-subject dependence, enabling inference at the population and subject levels. Our population-level regression effects change across quantile level, year and blood pressure type, providing a rich environment for inference. To our knowledge, this is the first quantile function model to explicitly model within-subject autocorrelation and is the first quantile function approach that simultaneously models multivariate conditional response. We find that the association between high blood pressure and living in an urban area has evolved from positive to negative, with the strongest changes occurring in the upper tail. The increase in urbanization over the last twenty years coupled with the transition from the positive association between urbanization and blood pressure in earlier years to a more uniform association with urbanization suggests increasing blood pressure over time throughout China, even in less urbanized areas. Our methods are available in the R package BSquare.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62G08 Nonparametric regression and quantile regression

Software:

BSquare; R
PDFBibTeX XMLCite
Full Text: DOI arXiv Euclid

References:

[1] Adair, L. S., Gordon-Larsen, P., Du, S. F., Zhang, B. and Popkin, B. M. (2014). The emergence of cardiometabolic disease risk in Chinese children and adults: Consequences of changes in diet, physical activity and obesity. Obesity Reviews 15 49-59.
[2] Attard, S. M., Herring, A. H., Zhang, B., Du, S., Popkin, B. M. and Gordon-Larsen, P. (2015). Associations between age, cohort, and urbanization with SBP and DBP in China: A population-based study across 18 years. Journal of Hypertension 33 948-956.
[3] Batis, C., Gordon-Larsen, P., Cole, S. R., Du, S., Zhang, B. and Popkin, B. (2013). Sodium intake from various time frames and incident hypertension among Chinese adults. Epidemiology 24 410-418.
[4] Benetos, A., Thomas, F., Safar, M. E., Bean, K. E. and Guize, L. (2001). Should diastolic and systolic blood pressure be considered for cardiovascular risk evaluation: A study in middle-aged men and women. J. Am. Coll. Cardiol. 37 163-168.
[5] Bondell, H. D., Reich, B. J. and Wang, H. (2010). Noncrossing quantile regression curve estimation. Biometrika 97 825-838. · Zbl 1204.62061 · doi:10.1093/biomet/asq048
[6] Burt, V. L., Cutler, J. A., Higgins, M., Horan, M. J., Labarthe, D., Whelton, P., Brown, C. and Roccella, E. J. (1995). Trends in the prevalence, awareness, treatment, and control of hypertension in the adult US population data from the health examination surveys, 1960 to 1991. Hypertension 26 60-69.
[7] Chakraborty, B. (2003). On multivariate quantile regression. J. Statist. Plann. Inference 110 109-132. · Zbl 1030.62046 · doi:10.1016/S0378-3758(01)00277-4
[8] Chen, X., Koenker, R. and Xiao, Z. (2009). Copula-based nonlinear quantile autoregression. Econom. J. 12 S50-S67. · Zbl 1182.62175 · doi:10.1111/j.1368-423X.2008.00274.x
[9] Chobanian, A. V., Bakris, G. L., Black, H. R., Cushman, W. C., Green, L. A., Izzo Jr, J. L., Jones, D. W., Materson, B. J., Oparil, S., Wright Jr, J. T. et al. (2003). The seventh report of the joint national committee on prevention, detection, evaluation, and treatment of high blood pressure: The JNC 7 report. JAMA 289 2560-2571.
[10] Choh, A. C., Nahhas, R. W., Lee, M., Choi, Y. S., Chumlea, W. C., Duren, D. L., Sherwood, R. J., Towne, B., Siervogel, R. M., Demerath, E. W. et al. (2011). Secular trends in blood pressure during early-to-middle adulthood: The fels longitudinal study. J. Hum. Hypertens. 29 838.
[11] Diggle, P. J., Heagerty, P. J., Liang, K.-Y. and Zeger, S. L. (2002). Analysis of Longitudinal Data , 2nd ed. Oxford Univ. Press, Oxford. · Zbl 1031.62002
[12] Egan, B. M., Zhao, Y. and Axon, R. N. (2010). US trends in prevalence, awareness, treatment, and control of hypertension, 1988-2008. JAMA 303 2043-2050.
[13] Fitzmaurice, G. M., Laird, N. M. and Ware, J. H. (2012). Applied Longitudinal Analysis . Wiley, New York. · Zbl 1057.62052
[14] Franklin, S. S., Lopez, V. A., Wong, N. D., Mitchell, G. F., Larson, M. G., Vasan, R. S. and Levy, D. (2009). Single versus combined blood pressure components and risk for cardiovascular disease: The Framingham Heart Study. Circulation 119 243-250.
[15] Fuentes, M., Henry, J. and Reich, B. (2013). Nonparametric spatial models for extremes: Application to extreme temperature data. Extremes 16 75-101. · Zbl 1329.62227 · doi:10.1007/s10687-012-0154-1
[16] Geraci, M. and Bottai, M. (2013). Linear quantile mixed models. Stat. Comput. 24 461-479. · Zbl 1325.62010 · doi:10.1007/s11222-013-9381-9
[17] Gilchrist, W. (2000). Statistical Modelling with Quantile Functions . CRC Press L.L.C. 2000 N.W. Corporate Blvd. Boca Raton, FL. · Zbl 1061.62548
[18] Ibrahim, J. G., Chen, M.-H. and Sinha, D. (2005). Bayesian Survival Analysis . Wiley Online Library. · Zbl 0978.62091
[19] Jones-Smith, J. C. and Popkin, B. M. (2010). Understanding community context and adult health changes in China: Development of an urbanicity scale. Soc. Sci. Med. 71 1436-1446.
[20] Jung, S.-H. (1996). Quasi-likelihood for median regression models. J. Amer. Statist. Assoc. 91 251-257. · Zbl 0871.62060 · doi:10.2307/2291402
[21] Kim, M.-O. and Yang, Y. (2011). Semiparametric approach to a random effects quantile regression model. J. Amer. Statist. Assoc. 106 1405-1417. · Zbl 1233.62082 · doi:10.1198/jasa.2011.tm10470
[22] Koenker, R. (2004). Quantile regression for longitudinal data. J. Multivariate Anal. 91 74-89. · Zbl 1051.62059 · doi:10.1016/j.jmva.2004.05.006
[23] Lim, S. S., Vos, T., Flaxman, A. D., Danaei, G., Shibuya, K., Adair-Rohani, H., AlMazroa, M. A., Amann, M., Anderson, H. R., Andrews, K. G. et al. (2013). A comparative risk assessment of burden of disease and injury attributable to 67 risk factors and risk factor clusters in 21 regions, 1990-2010: A systematic analysis for the global burden of disease study 2010. The Lancet 380 2224-2260.
[24] Luepker, R. V., Steffen, L. M., Jacobs, D. R., Zhou, X. and Blackburn, H. (2012). Trends in blood pressure and hypertension detection, treatment and control 1980 to 2009: The Minnesota Heart Survey. Circulation 126 1852-1857.
[25] McCarron, P., Okasha, M., McEwen, J. and Smith, G. D. (2001). Changes in blood pressure among students attending Glasgow University between 1948 and 1968: Analyses of cross sectional surveys. BMJ 322 885-889.
[26] Nelsen, R. B. (1999). An Introduction to Copulas . Springer, New York. · Zbl 0909.62052
[27] Popkin, B. M., Du, S., Zhai, F. and Zhang, B. (2010). Cohort profile: The China Health and Nutrition survey monitoring and understanding socio-economic and health change in China, 1989-2011. Int. J. Epidemiol. 39 1435-1440.
[28] Reich, B. J., Bondell, H. D. and Wang, H. J. (2010). Flexible Bayesian quantile regression for independent and clustered data. Biostatistics 11 337-352.
[29] Reich, B. J. and Smith, L. B. (2013). Bayesian quantile regression for censored data. Biometrics 69 651-660. · Zbl 1182.62175 · doi:10.1111/j.1368-423X.2008.00274.x
[30] Sesso, H. D., Stampfer, M. J., Rosner, B., Hennekens, C. H., Gaziano, J. M., Manson, J. E. and Glynn, R. J. (2000). Systolic and diastolic blood pressure, pulse pressure, and mean arterial pressure as predictors of cardiovascular disease risk in men. Hypertension 36 801-807.
[31] Smith, L. B., Fuentes, M., Gordon-Larsen, P. and Reich, B. J. (2015). Supplement to “Quantile regression for mixed models with an application to examine blood pressure trends in China.” . · Zbl 1454.62400
[32] Smith, M., Min, A., Almeida, C. and Czado, C. (2010). Modeling longitudinal data using a pair-copula decomposition of serial dependence. J. Amer. Statist. Assoc. 105 1467-1479. · Zbl 1388.62171 · doi:10.1198/jasa.2010.tm09572
[33] Stokes, J. 3rd., Kannel, W. B., Wolf, P. A., D’Agostino, R. B. and Cupples, L. A. (1989). Blood pressure as a risk factor for cardiovascular disease. The Framingham study-30 years of follow-up. Hypertension 13 I13.
[34] Sun, J., Frees, E. W. and Rosenberg, M. A. (2008). Heavy-tailed longitudinal data modeling using copulas. Insurance Math. Econom. 42 817-830. · Zbl 1152.91605 · doi:10.1016/j.insmatheco.2007.09.009
[35] Waldmann, E., Kneib, T., Yue, Y. R., Lang, S. and Flexeder, C. (2013). Bayesian semiparametric additive quantile regression. Stat. Model. 13 223-252. · doi:10.1177/1471082X13480650
[36] Wang, H. J. and Fygenson, M. (2009). Inference for censored quantile regression models in longitudinal studies. Ann. Statist. 37 756-781. · Zbl 1162.62035 · doi:10.1214/07-AOS564
[37] Wang, H. J. and Zhu, Z. (2011). Empirical likelihood for quantile regression models with longitudinal data. J. Statist. Plann. Inference 141 1603-1615. · Zbl 1204.62072 · doi:10.1016/j.jspi.2010.11.017
[38] World Health Organization and others (2011). Causes of death 2008: Data sources and methods. World Health Organization, Geneva.
[39] Yue, Y. R. and Rue, H. (2011). Bayesian inference for additive mixed quantile regression models. Comput. Statist. Data Anal. 55 84-96. · Zbl 1247.62101 · doi:10.1016/j.csda.2010.05.006
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.