Bayesian Linear Regression and Polynomial Model Selection of Diabetes Progression Data
Published in Unpublished, 2018
Recommended citation: Scott, S. (2018). Bayesian Linear Regression and Polynomial Model Selection of Diabetes Progression Data. Unpublished. http://shelbymscott.github.io/files/MSStatistics_ThesisProject.pdf
There are a number of different methods used to analyze large datasets and determine predictors of health outcomes. In this project, we take data from 442 diabetes patients and use both Bayesian linear regression and polynomial model selection to determine which predictors correlate with diabetes disease progression. We determine from the Bayesian linear regression that sex, BMI, and blood serum 4 are strongly associated with diabetes disease progression. Further information is available in the write-up of this thesis project.
Recommended citation: Scott, S. (2018). Bayesian Linear Regression and Polynomial Model Selection of Diabetes Progression Data. Unpublished.