Analytic challenges in nutritional epidemiology: the promise of Bayesian methods
November 30, 11:40 am – 12:30 pm PST
Nutritional epidemiology is plagued by a number of analytical issues, including selection bias, crude measures of putative risk factors, and imprecision in estimating effects of multiple exposures. However, in many cases information exists that could be leveraged to mitigate these problems. The Bayesian statistical paradigm offers a principled way to incorporate such information into an analysis but is infrequently used in nutrition research. In this talk I will present results from a series of epidemiologic studies that used Bayesian methods to consider the relationship between cancer outcomes and nutrition-related exposures. A common theme in these works is how the application of methods that utilize prior knowledge can improve our understanding of the relationship between nutrition-related factors and disease outcomes in observational settings.
Dr. Patrick Bradshaw is an Associate Professor in the Division of Epidemiology at the University of California School of Public Health. His interests span the areas of cancer epidemiology, cardiovascular disease epidemiology, and nutrition. His research also involves the application and development of novel epidemiologic methods to better understand the complex relationship between nutrition-related exposures and chronic disease outcomes.
If you require an accommodation for effective communication (ASL interpreting/CART captioning, alternative media formats, etc.) or information about campus mobility access features in order to fully participate in these events, please contact Lauren Goldstein at firstname.lastname@example.org with as much advance notice as possible and at least 7-10 days in advance of the event.