BST 682 - GENERALIZED LINEAR MODELS

College of Public Health

Credits: 3

This course, the second in a two-semester sequence in regression modeling, covers regression models for outcomes which are not normally distributed, such as binary and count data. The course will cover the generalized linear model framework, multivariate maximum likelihood theory, logistic regression, Poisson regression, and nominal and ordinal logistic regression models, as well as approaches for building models and checking assumptions. The course will include the use of computing tools to apply these models to real data.

Prerequisite(s):
Prereq: BST 675 and BST 681 or consent of instructor.