Abstract
In many case-control genetic association studies, a secondary phenotype that may have common genetic factors with disease status can be identified. When information on the secondary phenotype is available only for the case group due to cost and different data sources, a fitting linear regression model ignoring supplementary phenotype data may provide limited knowledge regarding genetic association. We set up a joint model and use a Bayesian framework to estimate and test the effect of genetic covariates on disease status considering the secondary phenotype as an instrumental variable. The application of our proposed procedure is demonstrated through the rheumatoid arthritis data provided by the 16th Genetic Analysis Workshop.
Highlights
Statistical analysis with regression models is a common approach for investigating the effects of genetic and non-genetic covariates on a response outcome
When the disease trait is obtained as a continuous outcome variable, linear regression models are commonly used [1,2], whereas logistic regression models, the Cochran–Armitage trend test and Pearson’s chi-squared test are often used for the analysis of a binary disease trait [3,4]
An important assumption of our modeling approach is that the disease is categorized by the binary trait D, and the disease severity is measured by the secondary phenotype W for the case group
Summary
Statistical analysis with regression models is a common approach for investigating the effects of genetic and non-genetic covariates on a response outcome. Entropy 2016, 18, 91 estimation of the effect of covariates on the continuous outcome measure in the control group when the continuous outcomes are missing in the control group He et al [9] proposed a Gaussian copula-based approach that could model the dependence between disease status and secondary phenotypes. We incorporate the secondary phenotype as an instrumental variable into the model and make use of the fact that the missing secondary phenotypes are known to be larger (or smaller) for the control group than for the case group This is not an unreasonable assumption in practice, since the available phenotype is regarded as an important surrogate clinical measurement in deciding the disease status.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
