Generalized-Linera-Models
At the end of this course, the student should have a profound knowledge of generalized linear models and basic knowledge of some extensions, including Part I Standard descriptive and inferential methods for multiway contingency t ables (odds ratios, conditional independence, Cochran-Mantel-Haenszel procedures,...) Components of a generalized linear model (GLM) GLM for binary data: logistic regression Building and applying logistic regression models Overdispersion and quasi-likelihood Conditional logistic regression and exact distributions Part II Extensions to multinomial responses (baseline category, cumulative link, partial odds ratio,...) Extensions to clustered binary (GEE, random effects) Extensions to clustered & multinomial data Loglinear models Models for matched pairs The student should be able to apply such models and methods using appropriate software (SAS, R).
