|
Abstract:
|
Generalized estimating equations (GEE) are often used for the marginal analysis of longitudinal data. Although much work has been done to improve the validity of GEE for the analysis of data arising from small-sample studies, little attention has been given to power in such settings. Therefore, we propose valid approaches with GEE in order to improve power in small-sample longitudinal study settings. Specifically, we use a modified empirical sandwich covariance matrix estimator within correlation structure selection criteria and test statistics. Use of this estimator can improve the accuracy of selection criteria and increase the degrees of freedom to be used for inference. Resulting power increases will be shown via a simulation study and application example.
|
