Non-Linear Panel Data Models in Stata

Panel data analysis is increasingly used in econometrics, financial analysis, public health, political and social sciences, since it enable researchers to allow for different types of latent heterogeneity between observations. Allowing researchers for example, to control for variables that cannot be directly observed or measured, such as cultural factors or differences in business practices across companies. The use of Panel Data in empirical studies also tends to result in a considerable improvement in the accuracy of the obtained estimates, since panel data sets usually contain more sample variability and higher degrees of freedom. Finally, panel data allows for the estimation of dynamic models, with causal relationships which may not arise instantaneously, but over a period of time.

This course follows on from our Linear Panel Data Models in Stata course to offer the necessary theoretical background and the applied skills to enable participants to: i) independently employ non-linear micro panel data techniques to their own research topics, and ii) to understand and evaluate micro panel data analyses published in the academic literature. The focus is therefore on non-linear estimation techniques (more specifically Poisson, Probit, Logit and Tobit panel data models) and issues of sample selection and attrition.

In common with TStat’s training philosophy, each individual session is composed of both a theoretical component (in which the techniques and underlying principles behind them are explained), and an applied (hands-on) segment, during which participants have the opportunity to implement the techniques using real data under the watchful eye of the course tutor. Throughout the course, theoretical sessions are reinforced by case study examples, in which the course tutor discusses and highlights potential pitfalls and the advantages of individual techniques. The intuition behind the choice and implementation of a specifi c technique is of the utmost importance. In this manner, the course leader is able to bridge the “often difficult” gap between abstract theoretical methodologies, and the practical issues one encounters when dealing with real data. At the end of the course, participants are expected to be able to autonomously implement the theories and methodologies discussed during the course.

TStat Training’s Non-Linear Panel Data training course is of particular interest to Master and Ph.D. Students, researchers in public and private research centres and professionals working in the following fields: Agricultural Economics, Economics, Finance, Management, Public Health, and the Political and Social Sciences seeking to acquire the “introductory” applied and theoretical toolset to enable them to undertake independent empirical research using panel data.

Participants are required to have a working knowledge of:

• the classical OLS regression model: Model Assumptions, Estimation and Inference;
• the arguments covered in TStat’s Linear Panel Data in Stata;
• the arguments illustrated in TStat’s course Analysis Micro Data in Stata;
• the statistical software Stata: including familiarity with Stata variable creation commands and Stata do files.

Those needing to refresh these concepts are referred to the reading lists on the respective course pages and to:

• Cameron, A. C. & Trivedi, P. K. (2022). Microeconometrics Using Stata, Volume I: Cross-Sectional and Panel Regression Methods. Second Edition. Stata Press. Chapters: 1-9.

• The incidental parameter problem in non-linear models
• Poisson panel data models: poisson, xtpoisson
  • Random effects
  • Correlated effects (conditional poisson)
• Probit panel data models: probit, xtprobit, oprobit, xtoprobit
  • Random-effect models
  • Correlated effects modelled as group means (a la Mundlak)
• Logit panel data models: logit, xtlogit, ologit, xtologit
  • Random effects
  • Correlated effects (conditional logit)
• Tobit and interval regression models: tobit, xttobit, intreg, xtintreg
  • Random effects
  • Correlated effects modelled as group means (a la Mundlak)
• Postestimation analysis:
  • Average marginal effects: margins
  • Goodness-of-fit measures: predict

SUGGESTED READINGS

• Cameron, A. C. & Trivedi, P. K. (2022). Microeconometrics Using Stata, Volume I: Cross-Sectional and Panel Regression Methods. Second Edition. Stata Press.
• Cameron, A. C. & Trivedi, P. K. (2022). Microeconometrics Using Stata, Volume II: Nonlinear Models and Casual Inference Methods. Second Edition. Stata Press.
• Woodridge, J. (2010). Econometric Analysis of Cross Section and Panel Data. MIT Press.

We are currently adding the finishing touches to our 2026 training calendar. We therefore ask you to check our website regularly or contact us at training@tstat.eu should the dates for the course you are interested in not be published yet. You will then be contacted via email as soon as the dates are available.