Prerequisites: Enrollment in OJOC/CRDSA program - traditional track
Description: This is a course in statistical modeling, with an emphasis on models for correlated data that arise when subjects are repeatedly measured or are clustered. These models, called mixed models, are extensions of linear and nonlinear regressions and analysis of variance. Examples will be drawn from clinical studies, such as multi-arm biomarker studies and crossover trials. Analyses of population pharmacokinetics and longitudinal data will also be discussed. Hands-on data analysis and presentation using standard computer software for linear and nonlinear analysis will be emphasized. Course goals include the ability to formulate and evaluate a model, read the scientific literature that employs these models, interact fruitfully with data modeling specialists, and present the results of these models mathematically and graphically. Traditional Track Only.
Description: Graphical methods, simple and multiple linear regression; simple, partial and multiple correlation; estimation; hypothesis testing, model building and diagnosis; introduction to nonparametric regression; introduction to smoothing methods (e.g., lowess) The course will include applications to real data.