Simultaneous Mean and Covariance Modeling of Chronic Kidney Disease
Year: 2013
Type: preprint
Abstract: Chronic kidney disease (CKD) is a serious health condition that is associated with premature mortality and decreased quality of life. Most of the existing population-level CKD studies focus on either the prevalence of CKD or the associations of CKD with other health problems. Very few studies have examined these quantities jointly, or have examined how the associations between CKD and other health problems vary by demographic characteristics. In this article, we propose a joint mean and covariance regression model to statistically describe how the quantitative measurement of CKD and associations between CKD and other health problems vary according to demographic predictors. We apply the methodology to the NHANES 2010 data and discuss guidelines for model selection and evaluation using standard criteria such as AIC in conjunction with posterior predictive goodness of fit plots. With the fitted results from the model, we are able to identify sub-populations that are at high risk of developing CKD, as well as those for which CKD is likely to co-occur with other health problems.
Source: arXiv (Cornell University)
Authors: Xiaoyue Niu, Peter D. Hoff
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2249209948