Re: st: Robust regression - outliers

[Nick Cox <njcoxstata@gmail.com>]

This presupposes that outliers are easily defined, which isn't always
true. For example, it is not even always true that an outlier is
associated with a large residual, but as you mention robust regression
let's start optimistic.

In my view the best ways to look for outliers are graphical.

. search modeldiag

and read the 2004 article and install the updated software for some
suggestions, The article is directly accessible at

http://www.stata-journal.com/sjpdf.html?articlenum=gr0009

For example, -rvfplot2- in this package works after more
regression-type commands than the official -rvfplot-.

-extremes- is from SSC and not especially helpful here.

Please note that the request to explain where user-written software
you refer to come from applies to you too. (See also your last post.)

Nick

On Thu, Sep 22, 2011 at 6:46 PM, Ozgur Ozdemir <ozdemirozgur@hotmail.com> wrote:

> I am trying to ding outliers in my regression analysis but none of the proposed commands such as cooksd, rstudent, hat etc works after a robust regression. Is there any specific command to run to find the outliers? I have also seen the extremes command but not sure if i can use. thanks

*
*   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/