Longitudinal Data Analysis 
Using Stata

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

Read 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. 


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. 


COMPUTING

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 participate in the hands-on exercises, you are strongly encouraged to bring a laptop computer with Stata installed (release 13; IC, SE, or MP versions are all acceptable). Stata 12 is OK, but earlier versions of Stata will lack some of the functionality demonstrated in the seminar.  A power outlet will be available at each seat, but wireless access is not guaranteed. Seminar participants who are not yet ready to purchase Stata could take advantage of StataCorp’s 30-day software return policy and obtain Stata 13 on a trial basis.  Stata also has a 30-day trial-license “share” policy permitting current license-holders to share a trial copy: http://www.stata.com/customer-service/share-stata/.


MATERIALS 

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 Courtyard Washington Embassy Row, 1600 Rhode Island Avenue, NW, Washington, DC  20036 at a special rate of $179 per night.  In order to guarantee rate and availability, make your reservations by calling Marriott at 1-888-236-2427 or 1-202-448-8004 no later than 5 PM (Eastern Time) Monday, May 26 and identify yourself with Statistical Horizons. 


SEMINAR OUTLINE

1. Opportunities and challenges of panel data.
    a. Data requirements
    b. Control for unobservables
    c. Determining causal order
    d. Problem of dependence
    e. Software considerations

2. Linear models
   a. Robust standard errors
   b. Generalized estimating equations
   c. Random effects models
   d. Fixed effects models
   e. Hybrid models

3. 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

4. Count data models
   a. Poisson models
   b. Negative binomial models
   c. Fixed and random effects 

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


Comments by recent participants

“Excellent course that covered a terrific review of cross sectional time series and panel data analytics. I recommend this course to anyone who does program monitoring & evaluations using longitudinal data.”
  Felix J. Bradbury, Accenture

“This was an extremely useful course. Course notes and examples were clear and Dr. Allison readily answered questions that enhanced my understanding of the material. It was an excellent course.”
  Holly Foster, Texas A&M University

“Dr. Allison teaches in a very clear manner. I have been trying to figure out fixed and random effects for a while, and now I have, thanks to Dr. Allison.  I like that the course gives examples of exact syntax, corresponding outputs, and interpretations. The printed lecture notes are invaluable.
  Heili Pals, Texas A&M University

“This course, with its excellent examples and clear explanations, helped cement concepts for me that I’d been exposed to previously but didn’t fully understand. It also taught me new methods like mixed models and SEM. I highly recommend the course and Dr. Allison.”
  Tia Palermo, Stony Brook University (SUNY)

“Excellent hands-on experience in longitudinal data analysis for those who work with data and also for those who may not work directly with data but work with others who do. So, if you are a senior faculty member working with younger colleagues or with graduate students and want to know enough about longitudinal data to get by, this course is for you. Job well done!!!”
  Ather Akbari, Saint Mary’s University, Nova Scotia

“The explanation on the use of statistical software is wonderful. The lecturer accepts questions from students many times during the lecture. This lecture is worth the price!”
  Hiroshi Yokomichi, University of Yamanashi, Japan