This course covers study design and intermediate-level data analysis techniques for handling confounding in epidemiologic studies. Confounding is carefully defined and distinguished from interaction. Course content covers stratification and multivariable techniques for controlling confounding in both matched and independent sample study designs, including analysis of covariance, logistic regression, and proportional hazards models. Model fit and prediction are discussed. Students are required to apply these methods with the aid of computerized statistical packages. The course will use statistical software R and SAS. Students cannot take both BS852 and BS835.

Note that this information may change at any time. Please visit the Student Link for the most up-to-date course information.