Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

Re: st: Quantile vs Quartile regression

From   Katie Farrin <>
Subject   Re: st: Quantile vs Quartile regression
Date   Wed, 29 May 2013 14:00:32 -0400

Hi, Shikha,

I just installed ivqreg (I found it through an internet source) but
have not done more than a couple test runs to see if it works properly
- I couldn't find it through Stata either.  One thing that helps is
when you move the files to the directory from which Stata calls your
personal ado files, move each file individually and not the whole
folder (thanks to a fellow Statalister for this advice).  I'm not sure
why it wouldn't work for me when I added the entire folder, but it
seems to be ok (no errors in calling it) if you add the files
one-by-one to your desired directory.

If you use this link and scroll to the section "IVQR" the fourth
option will allow you to download the user-written ivqreg from Do Wan
Kwak, who wrote the program.


On Wed, May 29, 2013 at 1:32 PM, Shikha Sinha <> wrote:
> Thanks everyone!. They were very informative econometrically. The
> reason why I asked the difference between OLS on quartile and quantile
> regression is because I want to run IVQR with continuous endogenous
> treatment variable. I can't use -ivqte as it needs a binary endogenous
> variable. Someone suggested me to divide the sample into different
> quartiles and run -ivreg2 on each quartile separately.
> I came across the use written syntax -ivqreg, but am unable to install
> it and could not find the ado package. Any help in this regard is
> again highly appreciated.
> Thanks,
> Shikha
> On Wed, May 29, 2013 at 5:53 AM, JVerkuilen (Gmail)
> <> wrote:
>> On Wed, May 29, 2013 at 3:29 AM, Maarten Buis <> wrote:
>>> It can also be informative to consider when linear regression and
>>> quantile regression produce the same results. This occurs when the
>>> distribution of the error term is symmetric (this could be the
>>> normal/Gaussian distribution, but it could also be any other symmetric
>>> distribution). In addition the coefficients for the predictors will in
>>> this case be (approximately) the same regardless of which quantile is
>>> considered.
>> Slight nit: In the presence of a symmetric heavy tailed error
>> distribution such as a t(2) or a Cauchy, OLS will have substantial
>> trouble compared to quantile regression.
>> --
>> JVVerkuilen, PhD
>> "They were careless people, Tom and Daisy - they smashed up things and
>> creatures and then retreated back into their money of their vast
>> carelessness, or whatever it was that kept them together, and let
>> other people clean up the mess they had made." -- F. Scott Fitzgerald
>> *
>> *   For searches and help try:
>> *
>> *
>> *
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index