I am running GEE logistic regression model for my fetal loss paper. As usual, I compare results between Stata and R and make sure they are consistent. To my surprise, the models assuming independent correlation structure give similar results but the models assuming exchangeable correlation structure give drastically different results.

It turns out that there is only one woman in my sample who reported a total number of eleven pregnancies (all others reported ten or less) and the presence of this single observation had huge influence on the algorithm used in R but not the one used in Stata. After excluding this single observation, the two sets of results look identical.