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: st: Elimination of outliers
From
Ronan Conroy <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: Elimination of outliers
Date
Tue, 7 Jun 2011 10:37:21 +0100
On 2011 Meith 6, at 21:24, Nick Cox wrote:
> I don't think what happens in contrived simulations hits the main
> methodological issue at all. As a geographer, some of the time, an
> outlier to me is something like the Amazon which is big and different
> and something that needs to be accommodated in the model.
In medicine, outliers often warn us that there are unusual (perhaps pathological) processes at work in some cases, so we are seeing a mixture of normal variation plus smaller groups of people with unusual characteristics. In pregnancy, for example, blood pressure is a mixture of three distributions: normal blood pressure response to pregnancy, and two abnormal blood pressure responses: gestational hypertension (high flow, low resistance) and pre-eclampsia (high resistance, low flow).
They remind us of Bacon's observation: we learn once when we examine the normal, and we learn once more when we examine the exceptions.
Ronán Conroy
[email protected]
Associate Professor
Division of Population Health Sciences
Royal College of Surgeons in Ireland
Beaux Lane House
Dublin 2
*
* 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/