[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Quantile regression

From   n j cox <>
Subject   Re: st: Quantile regression
Date   Mon, 22 Oct 2007 14:34:36 +0100

You want to fit a plane through the origin using the L-1 norm.
This is not as easy as with L-2 norm (LS), as it is more
than a matter of dropping a constant predictor yet otherwise using the
same criterion of fit. You are placing another constraint on a
problem that already does not have a closed-form solution,
and it does not surprise me that -qreg- does not support this.
I was going to suggest -rreg- instead but that does not
seem to help either. I guess you would need to set up
your problem, say using Mata in Stata 10.


Stefan Henschke

I have a question concerning the quantile regression.

I want to estimate something like:

qreg depvar indepvar1 indepvar2

with no other options specified.

Now my problem:
Is it possible to suppress the intercept?

I know how it is done using the regress command (using the [noconstant]
option), but I cant find any corresponding option for this in the qreg help
file. Is there *any* solution to this problem?

*   For searches and help try:

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