PROC PANEL: What values SAS uses for the cross-sectional dummies in fixed-effects model?

[gaussian]

Trying to do out of sample predictions and I am not sure what values to use for the dummy vars (while predicting) that SAS creates in fixed one-way effects model. I have 15 cross-sections. Using numbers 1-14 in the order isn't working as I see that my predicted values do not match what SAS shows in out=dataset.

[GeoffreyBrent]

I haven't experimented with PROC PANEL (and on a quick glance, the support documentation doesn't help me) but you may want to check whether it's using "effect coding". I remember being very confused by some other modelling PROCs until I found out about effect coding, which I'd never heard of before. Google should be able to find you a good explanation of the concept.