Hello all,

I have been trying to recreate SAS output in Stata but keep getting discrepancies. Unfortunately, the biostatistician only gave me the output and not the SAS code so I am trying to recreate the analyses in Stata by using the output.

First, I tried to check skewness and kurtosis and there was quite a discrepancy but I soon learned that is because SAS and Stata use different formulas.

Now, I am trying to create GEE analyses but I am not getting the same results.

This is what I am using to decipher the SAS analyses:
Distribution Normal Link Function Identity Observations Used 1375
GEE Model Information: Correlation Structure AR(1)
Subject Effect SBA (55 levels) Number of Clusters 55
Correlation Matrix / Cluster Size 25 (years)
tm=years; tm5=(tm-5)*(tm>=5); tm10=(tm-10)*(tm>=10); tm19=(tm-19)*(tm>=19);

Dependent Variable sallfd = sqrt(All_food) Algorithm converged.
GEE Fit Criteria

I have tried the following:
xtset SBA year
xtgee sAllfd tm tm5 tm10 tm19 i.Gcode Gcode#c.tm Gcode#c.tm5 Gcode#c.tm10 Gcode#c.tm19, family(gaussian) link(identity) corr(ar1)


Would this be incorrect since xtgee provides fit population-averaged panel-data models by using GEE?

Any help is most welcomed.