Jun Zhang of the Department of Biostatistics defends her dissertation on "Interpretable Analysis of Multivariate Functional Data".
The Joint Statistical Meetings, known simply as "JSM", is the largest gathering of statisticians held annually in North American. Faculty and student presenters from the Department of Biostatistics regularly participate giving invited talks, contributed talks, and poster presentations. Our students often receive top awards and participate in the affiliated career marketplace at the event.
Meetings of the Eastern North American Region of the International Biometric Society (a.k.a. "ENAR meetings") are held in late March or early April each year and reflect the broad interests of the Society, including both quantitative techniques and application areas. Faculty and student presenters from the Department of Biostatistics regularly participate giving invited talks, contributed talks, and poster presentations.
In genetic epidemiology studies, there are two main design types through which we can study complex traits. The first is population-based, in which independent cases and controls are collected to assess the difference in the underlying genetic makeup between affected and unaffected individuals. The other is family-based, in which data from families with at least one affected individual are collected. This allows for the study of the transmission of genetic variants between parent and offspring and how genetic variants differ between the affected individual(s) and the unaffected individuals within a family.
We examine two important issues in complex trait analysis in this dissertation. The first is the combination of mixed data types into a single likelihood, leveraging assumptions about the genotype frequencies to the extent that the data support them. To do this we will employ an empirical Bayes-type shrinkage estimation approach. Combining multiple data structures into a robust joint analysis may provide additional information about the disease loci driving complex traits. Secondly, we will examine heterogeneous presentation of traits associated with complex disorders. This phenotypic heterogeneity may arise due to genetic underpinnings, different environmental exposures, or perhaps by unknown factors. Specifically, we will address the following questions: (1) How can family data be combined with case-control data from the same study to improve estimates of disease association in a way that is robust to model misspecification?, (2) How can genetic sources of phenotypic heterogeneity be identified in case-control and family-based studies?
The public health significance of this research is that these methods will further understanding of the genetic architecture and will provide framework for studying other complex traits. Knowing the underlying genetic structure of a complex disease like orofacial clefting will aid in identifying any possible modifiable environmental factors that may also be contributing to the etiology of the disease. In order to identify those factors, we must have foundational knowledge of the biologic mechanism through which OFCs arise.
Last Updated On Friday, July 7, 2017 by Valenti, Renee Nerozzi
Created On Friday, February 24, 2017
Click to enter calendar events or share news and announcements.