Skip to main content

Analysis of Longitudinal Data

June 20-24, 2022
8:30 a.m. - 12:00 p.m.
2 credits
Course Number: 140.608.11


This summer this course will be taught online via Zoom, on the dates and times listed above. Registered students will attend their classes virtually via Zoom, in real time with faculty and other students.

"Great course if you want to quickly become fairly proficient in longitudinal data analysis. Prof Griswold is excellent at explaining complex concepts, and also making class enjoyable and relaxed."—Student 2021 

"The content of the lectures was very helpful, the primary instructor delivered the main ideas very effectively and I learned a lot during just one week. The lab exercises were well-designed."—Student 2019

"I very much enjoyed the course as the intructor described very difficult statistics concepts in very applicable and easy-to-understand ways."—Student, 2017

Course Instructor:


Covers statistical models for drawing scientific inferences from longitudinal data. Topics include longitudinal study design; exploring longitudinal data; linear and generalized linear regression models for correlated data, including marginal, random effects, and transition models; and handling missing data. Enrollment limited; students are required to bring a laptop to class, with Stata 16 or 15 installed. STATA with student discount is available through the Stata GRADPLAN.

Student Evaluation: Student evaluation based on analysis of a longitudinal data set, presentation of the results, and a written scientific report of the analysis methods and results

Learning Objectives: Upon successfully completing this course, students will be able to:

  • Prepare graphical or tabular displays of longitudinal data that effectively communicate the patterns of scientific interest

  • Use a general linear model to make scientific inferences about the relationship between response and explanatory variables while accounting for the correlation among repeated responses for an individual

  • Use marginal, random effects, or transitional generalized linear models to make scientific inferences when the repeated observations are binary, counts, or non-Gaussian continuous observations

  • Use SAS or STATA to conduct the appropriate longitudinal data analyses.

Prerequisites: Intermediate level biostatistics and epidemiology

Grading Options: Letter Grade or Pass/Fail

Course Materials: Provided in class

Recommended Textbook: Multilevel and Longitudinal Modeling Using Stata, Third Edition, Sophia Rabe-Hesketh and Anders Skrondal

Related CoursesMethods and Applications of Cohort Studies