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: Re: st: factor variables and qreg?

From   "Ariel Linden. DrPH" <>
To   <>
Subject   re: Re: st: factor variables and qreg?
Date   Fri, 24 Aug 2012 09:26:45 -0700

Thanks, Maarten.

I wonder if any StataCorp people on the list could respond to this query
with a definitive answer?


Date: Thu, 23 Aug 2012 10:56:01 +0200
From: Maarten Buis <>
Subject: Re: st: factor variables and qreg?

On Wed, Aug 22, 2012 at 11:39 PM, Ariel Linden. DrPH wrote:
> Does anyone know if there is a reason why -qreg- does not allow factor
> variables using the new format available since v11.0?
> It does allow for the older approach using the prefix -xi- , which seems a
> bit strange to me. Perhaps this is an oversight by the Stata programmers?

The only authoritative comments can come from StataCorp, but it can be
fun to speculate. I suspect that this is not an oversight.  Many
models are estimated using the common machinery of -ml-, and they
could get most of the work done by changing -ml-. -qreg- seems to have
its own build-in maximization algorithm, which does not surprise me as
it is a maximization problem with its own peculiar set of
difficulties. So it is a lot more work to implement it. It may be that
they are were working on a more general overhaul of -qreg- and did not
get that ready for the Stata 12 release, and thus decided to keep
- -qreg- as it is for now. Alternatively, it may just have been lower on
their list of priorities.

- -- Maarten

- ---------------------------------
Maarten L. Buis
Reichpietschufer 50
10785 Berlin

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index