Abstract
We propose a genetic association analysis using Dirichlet regression to analyze the Genetic Analysis Workshop 18 data. Clinical variables, arranged in a longitudinal data structure, are employed to fit a multistate transition model in which the transition probabilities are served as a response in the proposed analysis. Furthermore, a gene-based association analysis via penalized regression is implemented using the markers at a single-nucleotide polymorphism level that we previously identified via nonpenalized Dirichlet regression.
Highlights
Genetic association analyses have had tremendous successes in recent years; most of these analyses were based on binary or continuous responses
Multistate transition model We describe hypertension, our trait of interest, using a 3-state model based on recorded blood pressure levels for each individual at each examination
We assess this association using Dirichlet regression [4], which suits this response structure. The advantage of this approach lies in its tractability in dealing with the proposed response. It allows a more comprehensive understanding of the genetic effect on the expression of hypertension, Gene-based association Once we identify significant SNPs through the genetic association analysis as described above, we proceed to perform the analysis at a gene level
Summary
Genetic association analyses have had tremendous successes in recent years; most of these analyses were based on binary or continuous responses. We propose a multivariate response vector indicating probabilities of transitions to predefined hypertensive states. This enables us to reflect the inherent uncertainty involved in the probability that a patient will transfer to a given state. An important feature of our approach is the incorporation of prehypertension as an intermediate state. As Winegarden argues, prehypertension blood pressure in young patients helps predict the development of hypertension [1]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.