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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: factor variables and qreg?


From   "William Gould, StataCorp LP" <wgould@stata.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: factor variables and qreg?
Date   Mon, 27 Aug 2012 09:48:03 -0500

Roger Newson <r.newson@imperial.ac.uk> asked, 

> Would I be right in guessing that StataCorp are also working on
> clustered variances for -qreg-?

after I wrote that yes, we are working on adding factor variables 
to -qreg-.  And Ariel Linden <ariel.linden@gmail.com> asked, 

> can we hope to see the command allow weights as well?

The answer is may be.  Yes, we are working on robust and cluster-robust
standard errors -- and weights -- but until we have a full
implementation, working in house, we will not know how well the
cluster-robust standard errors and pweights work.  This is not a
programming issue or a performance issue, this is a statistical issue.
How well these features work depends on bandwidth selection.  We will
need to run simulations to determiine how well the published selection
methods work in the robust and cluster-robust cases, and then determine
whether more work needs to be done.

Just to remind everybody, I was *NOT* making an announcement of the
imminent release of -qreg- with new featues. Ariel asked if we were 
working on this and I replied, "yes we are."  

-- Bill
wgould@stata.com
*
*   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