15.11. GEE Analyses for Data with Missing Values
One of the main advantages of the GEE method is that it addresses the possibility of missing values. The number of responses per subject, or cluster, can vary; recall that you can have ti responses per subject, where ti depends on the ith subject. While the data sets analyzed in previous sections were complete, or balanced, you are faced with missing data in many situations, especially for observational data that are longitudinal. Loss to follow-up is a common problem for planned studies that involve repeated visits. The GEE method works nicely for many of these data situations. Note however, that the GEE method does assume that the missing values are missing completely at random, or MCAR.
Get Categorical Data Analysis Using The SAS® System, 2nd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.