Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: QR IVs and Cluster Robust bootstrap for bsqreg


From   Abekah Nkrumah <ankrumah@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: QR IVs and Cluster Robust bootstrap for bsqreg
Date   Thu, 1 Mar 2012 01:26:08 +0000

Hi Statalist

I am running quantile regressions with a continuous dependent variable and
have a challenge with running an IV version and cluster robust
bootstrap standard errors

On the issue of quantile IVs based on 2SQR, my understanding is that I
need to run an OLS with my endogenous variable as the dependent
variable and the instruments together with the other exogenous
regressors as independent variables. Thereafter I will predict from the
first stage and then plug it into the structural equation and then
bootstrap the standard errors to take care of possible bias in the
standard errors of the predicted variable. Will I be right if I do
this and is this the same as what is proposed by Amemiya (1982) and
Powell (1983)

Secondly, my data was collected via stratified sampling (ie.
clustering). This means that using the normal bootstrapping will not
correct for the intra-cluster correlations. Instead a cluster robust
bootstrapping will be adequate. However the qreg, bsqreg and sqreg
commands in stata seem not to work when I specify the vce cluster
option for bootstrap. Please can someone help on this?

Can you help me on this. Thank you very much

Regards

Gordon
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index