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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: Keep/Drop Observations for Top/Bottom X%


From   "Justina Fischer" <JAVFischer@gmx.de>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Keep/Drop Observations for Top/Bottom X%
Date   Thu, 11 Oct 2012 12:20:01 +0200

Hi Maarten,

exactly, when working with really big datafiles (e.g. > 100'000 obs.) and estimating a non-linear model dropping the obs not in use saves heavily on computation time, or might even estimations become manageable in the first place (e.g. when estimating interaction effects). 

Justina


-------- Original-Nachricht --------
> Datum: Thu, 11 Oct 2012 12:07:43 +0200
> Von: Maarten Buis <maartenlbuis@gmail.com>
> An: statalist@hsphsun2.harvard.edu
> Betreff: Re: st: Keep/Drop Observations for Top/Bottom X%

> On Thu, Oct 11, 2012 at 11:54 AM, Justina Fischer  wrote:
> > in principle you might be right.
> >
> > However, for reasons of practicability it is sometimes recommendable for
> subset analysis to simply upload the full data and drop a part rather than
> working with an 'if' restriction throughout all regressions.
> 
> It is largely a matter of style. I like the principle of keeping your
> data as much as possible intact, and I thus prefer the -if- route over
> the -keep- route. Using if selections throughout my analysis has
> become natural for me, and even desirable as a constant reminder of
> which sub-sample I am working on. The main reason why I sometimes
> deviate from that default is when the data is so large (e.g. Census
> data) that it becomes unmanageable.
> 
> -- Maarten
> 
> ---------------------------------
> Maarten L. Buis
> WZB
> Reichpietschufer 50
> 10785 Berlin
> Germany
> 
> http://www.maartenbuis.nl
> ---------------------------------
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index