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, is already up and running.

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

Re: st: Removing outliers from my dataset

From   Nick Cox <>
To   "" <>
Subject   Re: st: Removing outliers from my dataset
Date   Wed, 17 Apr 2013 18:59:44 +0100

See also the thread starting at

including this advice from one of our founders

In 1827 Olbers asked Gauss "What should count as an unusual or too
large a deviation? I would like to receive more precise directions."
Gauss in his reply was disinclined to give any more directions and
compared the situation to everyday life, where one often has to make
intuitive judgments outside the reign of formal and explicit rules.


On 17 April 2013 17:00, JVerkuilen (Gmail) <> wrote:
> On Wed, Apr 17, 2013 at 10:33 AM, Nick Cox <> wrote:
>> I think I agree with this, not that there can't be differing views on
>> a tricky area!
>> In essence, there should be a story that says why some data points
>> don't belong. That's more a subject-matter judgment call relating a
>> decision to research objectives than a statistical decision.
> Definitely. The robust literature IMO isn't about removing outliers
> per se, it's about having methods to make your inferences not affected
> strongly by outliers so as not to have to do a lot of the arbitrary
> trimming that folks often do. Who knows, the outliers might well be
> the most valuable points in your dataset!
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index