Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: AW: st: xttrans accuracy
From
Dmitriy Krichevskiy <[email protected]>
To
[email protected]
Subject
Re: AW: st: xttrans accuracy
Date
Thu, 24 Jun 2010 10:52:07 -0400
Thank you very much for all of your input,
The -xttrans3- (called xttrans2- by Maartrten) produces the same type
of matrix with some additional r(). But wouldn't it be easier just to
stop short one step and display actual fractions so system of
equations can be easily formed. Avoiding the rounding issue entirely
(I'll try to do that next). Granted, the original -xttrans- was not
meant for this purpose at all.
As always, Statalisters Rock, thanks for all of your help.
Dmitriy
On 6/23/10, Scott Merryman <[email protected]> wrote:
> On Wed, Jun 23, 2010 at 5:06 AM, Nick Cox <[email protected]> wrote:
>> 2. Whether rounded fractions sum to 1 exactly not only involves machine
>> precision issues but also provides some mathematical challenges. See for
>> example
>>
>> Persi Diaconis and David Freedman
>> 1979
>> On Rounding Percentages
>> Journal of the American Statistical Association 74: 359-364.
>>
>> -- and its references.
>
> This is online at:
>
> http://www-stat.stanford.edu/~cgates/PERSI/papers/freedman79.pdf
>
> Scott
> *
> * 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/
>
--
Dmitriy Krichevskiy Ph.D. Candidate
Economics Department
Florida International University
www.fiu.edu/~dkrichev
Research Associate, College of Education
Lumina Foundation Project
*
* 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/