[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Quantile regression with weights
Hi. Has any body come up with an answer to the question below on how to use
survey (analytical) weights with bootstrap quantile regression in STATA? (I have
an application similar to the one in the message below)
One could run bsqreg with weighted data, ie., on the transformed model:
y*w = a w + b x*w
where w= obs. i weight/total population size, presuming that the resampling of
reweighted data builds in the required adjustment to the contribution of each
observation to the estimate of the sampling variability of b at each quantile.
But the problem is that STATA quantile regression commands don't allow to
specify the option of no intercept!
Any help will be appreciated.
Poverty Group, Latin America and the Caribbean
1818 H St. NW
Mail Stop I-805, Room I8-107
Washington, D.C. 20433
ph: 202 458 4962
fax: 202 522 0054
From "Cruces,GA (pgr)" <
Subject st: BSQREG and WEIGHTS
Date Mon, 16 Dec 2002 21:20:11 -0000
I would like to run a quantile regression with bootstrapped standard
errors with a household survey dataset that has weights. However, the
BSQREG command does not allow weights.
The weights are integers (say, between 40 and 2600) such that adding
them up gives the total population of each city (though I'm working with
one city only right now - no PSUs or clusters).
The only reference I could fin on Statalist was the email from W. Gould
copied below - however, I can't figure out the correct way to implement
his suggestions in the quantile regression case. I emailed Stata support
and they only replied that implementing weights in BSQREG was not in
their plans, and that the email below could be useful...
Has anyone encountered similar problems? I went into the BSQREG code but
it was too obscure for me. Any help will be greatly appreciated!
Thank you very much
* For searches and help try: