Course Description
Extensions of classical and generalized linear models with emphasis on longitudinal data analysis. Course will focus on linear mixed models, and marginal and mixed-effect versions of generalized linear models for longitudinal discrete data. Emphasis will be placed on the application of these models to analyze real data.
Athena Title
LONG DATA ANALYSIS
Prerequisite
STAT 8260
Pre or Corequisite
STAT 8620
Semester Course Offered
Offered spring
Grading System
A - F (Traditional)
Course Objectives
Students will learn statistical models and methodology for the analysis of continuous and discrete data for which the assumptions of generalized linear models (GLMs) do not hold. In particular, students will learn to analyze longitudinal data and other data types for which the assumption of independence among units fails. Students will learn the theory and application of linear mixed-effect models and generalized linear mixed-effect models, as well as other extensions of GLMs. Students will learn the computational and algorithmic methods for fitting these models as well as the implementation of these methods via statistical software.
Topical Outline
Introduction to longitudinal data; classical methods for continuous longitudinal data; linear mixed models including special cases, fitting and inference methodology, and application to real data; generalized linear mixed models including estimation, inference and application; marginal models generalized linear models for longitudinal data and generalized estimating equations; analysis in the presence of missing data. Additional topics at the discretion of the instructor.
Syllabus