[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: xtivreg , fe + cluster option
I have an unbalanced employer employee dataset.
I'm estimating a wage curve. I'm estimating a wage controlling for
individual, region , time fixed effects, and region specific linear
time trends. We use a IV-fixed effects estimator (FE-2SLS) in which the
rate is instrumented with its first and the second lag
Unfortunately Stata's xtiverg, fe does not incude the cluster option and I
have more instruments than clusters.
In this case s.e. can not be corrected for clustering on region but only
for clustering on individuals, since so I might face downward biased s.e.
on the elasticity of interest.
Is there any suggestion on how to deal with this problem?
thenk you in advance.
* For searches and help try: