[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: quantile regressions and within person clustering
I'm dealing with a problem related to quantile regressions.
The dataset I'm using for my empirical analysis is the European
Community Household Panel, that contains infomation on households and
individuals characteristics over the period 1994-2001.
I would like to perform a quantile regressions of the hourly wage on a
set of sociodemographic characteristics. I would like to apply the
sample weights and allow for within person clustering when calculating
the standard error.
I know that the stata command qreg allows "aweight" option, but do not
allow the "cluster(person_id)" option.
1) HOW CAN I ESTIMATE A QUANTILE REGRESSION ALLOWING FOR WITHIN PERSON
CLUSTERING WHEN CALCULATING THE STANDARD ERROR?
2) IF I CAN NOT ESTIMATE A QUANTILE REGRESSION ALLOWING FOR WITHIN
PERSON CLUSTERING, CAN I CALCULATE STANDARD ERROR WITH BOOTSTRAP?
Looking forward to hearing from you,
"Tor Vergata" University
via Columbia 2
* For searches and help try: