Longitudinal Data Analysis
Using Stata

A 2-Day Seminar on Regression Analysis for Panel Data
Taught by Paul D. Allison, Ph.D. 

Read 8 reviews of this seminar. 

Panel data offer major opportunities and serious pitfalls

The most common type of longitudinal data is panel data, consisting of measurements of predictor and response variables at two or more points in time for many individuals. Such data have two major attractions: the ability to control for unobservables, and the determination of causal ordering.

However, there is also a major difficulty with panel data: repeated observations are typically correlated and this invalidates the usual assumption that observations are independent. There are four widely available methods for dealing with dependence: robust standard errors, generalized estimating equations, random effects models and fixed effects models. This course examines each of these methods in some detail, with an eye to discerning their relative advantages and disadvantages. Different methods are considered for quantitative outcomes, categorical outcomes, and count data outcomes.

This is a hands-on course with ample opportunity for participants to practice the different methods. 


This seminar will use Stata for the many empirical examples and exercises. However, no previous experience with Stata is assumed. Lecture notes and exercises using SAS are also available on request. To do the exercises, you will need to bring your own laptop with a recent version of Stata (or SAS) installed. Power outlets will be provided at each seat.

Who should attend? 

If you need to analyze longitudinal data and have a basic statistical background, this course is for you. You should have a good working knowledge of the principles and practice of multiple regression, as well as elementary statistical inference. And it is also helpful to have some familiarity with logistic regression. But you do not need to know matrix algebra, calculus, or likelihood theory. 


Participants receive a bound manual containing detailed lecture notes (with equations and graphics), examples of computer printout, and many other useful features. This book frees participants from the distracting task of note taking.

Registration and lodging

The fee of $895.00 includes all seminar materials.

Lodging Reservation Instructions

A block of rooms has been reserved at the Boston Common Hotel and Conference Center, 40 Trinity Place, Boston MA at a rate of $169 per night. To register, please call (617) 933-7700 and identify yourself with Statistical Horizons. For guaranteed rate and availability, you must make your reservation before the cut-off date of May 19, 2013. 

Seminar outline

1. Opportunities and challenges of panel data.
    1.Data requirements
    2.Control for unobservables
    3.Determining causal order
    4.Problem of dependence
    5.Software considerations

2. Linear models
   1.Robust standard errors
   2.Generalized estimating equations
   3.Random effects models
   4.Fixed effects models
   5.Hybrid models

3. Logistic regression models
   1.Robust standard errors
   2.Generalized estimating equations
   3.Subject-specific vs. population averaged methods
   4.Random effects models
   5.Fixed effects models
   6.Hybrid models

4. Count data models
   1.Poisson models
   2.Negative binomial models
   3.Fixed and random effects 

5. Linear structural equation models
   1.Fixed and random effects in the SEM context
   2.Models for reciprocal causation with lagged effects

Comments from recent participants

“Dr.Allison has perfected the optimal level of pacing and detail for covering a complex set of statistical tools. His experience and clarity make for a great learning experience.”
   Paul Glavin, McMaster University

“It was a very intense course but I gained valuable insight into longitudinal data analysis. Professor Allison used language that was easy to follow even for a beginning Stata user like myself. Going over the interpretation of the coefficients was extremely helpful.”
   May Uchida, Columbia University

“Dr. Allison made the material accessible to a wide range of students and his style of teaching fostered an open environment in which students felt comfortable to ask questions throughout the course. For some reason, even though he followed the notes closely, his verbal description of the data and his explanation of why to follow a certain strategy for analyzing panel data made the subject matter much easier to absorb than just straight reading of notes and/or textbooks.”
   Megan Kavanaugh, Guttmacher Institute

“I strongly recommend this course to anyone who wants to get exposure to or refresh his/her knowledge of longitudinal data analysis. The course is extremely well-structured, very clearly taught and nicely blends more technical explanations with specific examples using real data. Although I was already familiar with some of the materials, I truly enjoyed the course.”
   Gino Cattani, Stern School of Business, NYU

“The examples provided were clear and relevant. Paul was an excellent teacher and patient in answering questions. I highly recommend this course for anyone considering longitudinal analysis.
   Rachel C Shelton, Columbia University 

“This course was very helpful in showing us the different available ways of analyzing longitudinal data. It also demonstrated very practical STATA commands that I will be using for my research.”
   Shervin Assassi, University of Texas Health Science Center at Houston

“Lecture notes are carefully constructed. I can deepen my understanding of statistics greatly. Thanks.”
   Takashi Yoshida, Shizuoka University

 “I find it extremely difficult to understand statistics. In particular, I am lost when we turn to mathematical models. Paul makes the material extremely user friendly and easy to follow. I would recommend his course to all of those who are intimidated by statistics.”
   Jamal Shamsie, Michigan State University