Hi,

I would like to regress an equation using paneldata, but I would like to find estimates for every country seperately. I can find one estimate for all countries (panel data) and with fixed effects, but my problem is when I want to look at effects in only one country, and I use "bysort i:" (where "i" is a country), it will not take the fixed effects into account. Do you guys know how to take this into account?

I find the same results using the two different commands (but I think thats a problem, as fixed effects are not taking into account using "bysort i:"):

> bysort i: xtivreg2 dlogsigma KAPITALSKAT INF ÅBEN VALUTA YMIDDEL STAT INFSD ÅBENSD VALUTASD STATSD, fe robust
> bysort i: reg dlogsigma KAPITALSKAT INF ÅBEN VALUTA YMIDDEL STAT INFSD ÅBENSD VALUTASD STATSD

Many thanks.