Generalized Estimating Equations

Generalized estimating equations (GEE) provide a comparatively simple approach to dependent Gaussian and non-Gaussian outcomes. In particular, they are commonly used with repeated measures. This technique is appealing when the target of inference is population-averaged (marginal) quantities, such as, for example, the difference in time evolution between two or more groups. Apart from standard GEE, a number of variations to the theme are presented. The technique can be applied to randomized experiments, observational studies, survey data, etc. A clinical trial example and an analysis of data from a developmental toxicity study illustrate the methodology.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Similar content being viewed by others

Generalized Estimating Equations

Chapter © 2014

Generalized Estimating Equation

Chapter © 2017

Assessing the robustness of estimators when fitting Poisson inverse Gaussian models

Article 04 June 2018

References

Author information

Authors and Affiliations

  1. I-BioStat, Universiteit Hasselt & KU Leuven, Hasselt, Belgium Geert Molenberghs
  2. I-BioStat, KU Leuven & Universiteit Hasselt, Leuven, Belgium Geert Verbeke
  3. Selkirk, United Kingdom Michael G. Kenward
  1. Geert Molenberghs