GENERALIZED LINEAR MODELS

Graduate

This course covers the theory, methodology and applications of generalized linear models. Topics include logistic regression, probit regression, binomial regression, Poisson regression, overdispersion, quasi-likelihood, and the exponential family. Students will be required to use standard statistical software to analyze binary and count data. Graduate students will be required to demonstrate mastery of model building and assessment, parameter estimation, inference, and interpretation of findings from generalized linear models in a variety of settings inspired by real-world problems. This course is cross-level listed with STAT 4280. Credit cannot be received for both MCS 8280 and STAT 4280. PREREQUISITE: Admission to a graduate program in Science HOURS OF CREDIT: 3