Statalist


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

Re: st: RE: Outlier: Detection


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: Outlier: Detection
Date   Wed, 20 Feb 2008 08:51:42 +0000 (GMT)

--- Sergiy Radyakin <serjradyakin@gmail.com> wrote:
> The question was: which of the two programs is better suited for
> detecting outliers. I think it is safe to presume that each author
> will favor his or her creation. It's similar to asking Stata Corp,
> what is better Stata or SPSS :)

Since both programs have the same name, I assumed they followed
convention that either they are writen by the same author, or that the
new and the old author have agreed that the new program (whichever that
may be) supercedes the old one. In both case that person would know
which program is to be prefered. 

> Yes, I am also sceptical. But currently I am working with a
> "dataset", where each (of many) "datafile" contains up to 4000
> variables. Even the simpliest question, like "How the missings were
> encoded?" is not trivial anymore. Looking at 4000 graphs would be
> simply infeasible. On the other hand, nobody insists on removing the
> suspicious observations. Most of the times we just want to tag them,
> to review more carefully. Is that OK?
 
A quick look at the program suggests that at least some older version
did automatically drop outliers. Also from time to time questions show
up on the statalist on how to automatically delete/ignore outliers
(however defined). In big datasets like the one you are describing you
will just have to be pragmatic. If you have 4000 variables, you'll have
to look at much more than 4000 graphs: an outlier is not necesarily
defined as a univariate characteristic, so you should also consider
multivariate comparisons. Most likely a person looking at much more
than 4000 graphs would probably make more mistakes than an automatic
procedure that tags suspicious cases which are than investigated.

-- Maarten


-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      __________________________________________________________
Sent from Yahoo! Mail - a smarter inbox http://uk.mail.yahoo.com

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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   |   What's new   |   Site index