Hello Statalist-Forum,
I was wondering if you could help me with a problem:
I have a continous outcome variable (a health score) and information about incidents per governorate in a country. I want to describe the realtionship between those two (obviously adding more variables at another point).
My question: Do I include fixed governorate effects in this regression, eventhough it is on the exact same level (a dummy for all the governorates)? Additionally, do I cluster the SE?
Basic Code:
reg health incidents
1. alternative
reg health incidents i.governorate
2. alternative
reg health incidents i.governorate, vce(cluster gov)
Like I said, the information on the incidents are also on the governorate level (one number for each governorate).
It feels that this would create somewhat a problem or a circular thing. However I can not explain to myself econometrically if this really states a problem or if this is fine.
Thank a lot in advance
0 Response to Clustered Errors and fixed effect on the same level
Post a Comment