Longitudinal Data Analysis Using SAS
A 2-Day Seminar Taught by Paul D. Allison, Ph.D.
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 seminar 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 and categorical outcomes.
This is a hands-on seminar with ample opportunities to practice the various methods.
This seminar will use SAS for the many empirical examples and the exercises. However, lecture notes and exercises using Stata are also available on request. At least one hour each day will be devoted to exercises. To optimally benefit, you should bring your own laptop with a recent version of SAS (or Stata) installed. Power outlets will be provided at each seat.
There is now a free version of SAS, called the SAS University Edition, that is available to anyone. It has everything needed to run the exercises in this course, and it will run on Windows, Mac or Linux computers. However, you do need a 64-bit machine with at least 1 GB of RAM. You also have to download and install virtualization software that is available free from third-party vendors. The SAS Studio interface runs in your browser, but you do not have to be connected to the Internet. The download and installation are a bit complicated, but well worth the time and effort.
WHO SHOULD ATTEND?
If you need to analyze longitudinal data and have a basic statistical background, this seminar is for you. You should have a good working knowledge of the principles and practice of multiple regression, as well as elementary statistical inference. It is also helpful to have some familiarity with logistic regression. But you do not need to know matrix algebra, calculus, or likelihood theory.
LOCATION, FORMAT, MATERIALS.
The seminar meets Friday, April 15 and Saturday, April 16 at the Courtyard Marriott Atlanta Downtown, 133 Carnegie Way, Atlanta, GA, 30303.
The class will meet from 9 to 5 each day with a 1-hour lunch break.
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 $995 includes all course materials.
Lodging Reservation Instructions
A room block has been arranged at The Courtyard Marriott Atlanta Downtown,133 Carnegie Way, Atlanta, GA, 30303. Call Marriott Reservations at (800) 321-2211 or (404) 222-2416 by March 31, 2016 for the special rate of $199 per night and mention that you are part of the Statistical Horizons Meeting group. You may also book your room by clicking here.
- Opportunities and challenges of panel data.
a. Data requirements
b. Control for unobservables
c. Determining causal order
e. Problem of dependence
d. Software considerations
- Linear models
a. Robust standard errors
b. Generalized estimating equations
c. Random effects models
d. Fixed effects models
e. Hybrid models
- Logistic regression models
a. Robust standard errors
b. Generalized estimating equations
c. Subject-specific vs. population averaged methods
d. Random effects models
e. Fixed effects models
f. Hybrid models
- Linear structural equation models
a. Fixed and random effects in the SEM context
b. Models for reciprocal causation with lagged effects
“I learned the logic and rationale and advantages and disadvantages for certain methods compared to others. Dr. Allison teaches this thought process, not just the statistical concepts behind how the methods work. Learning the why and how of certain specifications in SAS syntax is invaluable for applied researchers.”
Deryl Hatch, University of Nebraska-Lincoln
“Great workshop with a good balance of theory, lectured examples and hands-on exercises on SAS. I got a deeper understanding of nuances related to longitudinal analyses that I was already using and feel now more confident in choices I am making for my models.”
Claudia Trudel-Fitzgerald, Harvard School of Public Health
“I really got a lot out of this course. Dr. Allison is very thorough and precise, and I feel like I walked away with a deeper understanding of the pros & cons of many different models for longitudinal data analysis.”
Kristen Hamilton, University of Maryland
“This course thoroughly covered models for Longitudinal Data in an efficient manner. Material was presented clearly. The course notes will be a great reference for the future. I look forward to taking another course soon!”
Katherine Kurgansky, VA Boston Healthcare System
“Paul’s years and experience with applying and teaching complex concepts was quite evident throughout the seminar, enabling people new to the material to go home and further their independent study.
Randall S. Jorgensen, Syracuse University
“A very well organized course. Very clearly presented. Useful for those with some background in LDA.”
David Gagnon, MAVERIC/Boston VAMC
“While I have been using proc mixed & proc genmod for longitudinal data analysis for several years, I came away with a better understanding of some of the key components and assumptions.”
Lori Lyn Price, Tufts Medical Center
“Excellent course! Very well organized, easy to follow, and comprehensive. Dr. Allison did a wonderful job answering our questions. I learned a lot and I’m very happy I signed up for it. Congratulations!”
Dimitris Kiosses, Weill Cornell Medical College
“I truly enjoyed the longitudinal data analysis course. This course provided several examples, including SAS code on the different models to fit different forms of data. We learned how to fit the various models, identified differences in the results (particularly how the standard errors were affected) and learned how to handle multilevel data. The in-class exercises, with the help of Dr. Allison, were beneficial in applying these learned techniques. I feel equipped to analyze longitudinal data – all my questions were answered.”
Dayna Johnson, Brigham and Women’s Hospital/Harvard Medical School