[Python] Get odds ratio for GEE model in statsmodels

I'm using statsmodels to construct a Generalized Estimating Equation (GEE) model to compute odds ratios like so:

va = sm.cov_struct.Autoregressive()
model = sm.GEE(x, y, group)
result = model.fit()
print(result.summary())

>>> GEE Regression Results
===========================================================================================
Dep. Variable: x No. Observations: 10000
Model: GEE No. clusters: 7000
Method: Generalized Min. cluster size: 1
Estimating Equations Max. cluster size: 10
Family: Gaussian Mean cluster size: 1.4
Dependence structure: Independence Num. iterations: 2
Date: Fri, 30 May 2025 Scale: 0.112
Covariance type: robust Time: 01:46:29
================================================================================
coef std err z P>|z| [0.025 0.975]
--------------------------------------------------------------------------------
y 0.0772 0.002 31.899 0.000 0.072 0.082
==============================================================================
Skew: 2.2170 Kurtosis: 3.0326
Centered skew: 0.9448 Centered kurtosis: 10.6225
==============================================================================




I wish to get the odds ratio for x. How can I do this?

I think I should be able to use the GlobalOddsRatio but don't actually understand how to use it from the reference.

Continue reading...