Re: st: outliers v. skew

[Steven Samuels <sjsamuels@gmail.com>]

Another good option is  -mmregress-  and related commands ("findit  
mmregress"). These commands also have helpful options for the  
identification and classification of outliers, something which least  
squares cannot be trusted to do.

Steve

On Nov 30, 2010, at 12:46 PM, Campo, Marc wrote:

I see your point and don't want anyone to waste their valuable time.   
I will reference anything duplicative on future posts. For reference  
here, the main suggestion at medstats was quantile regression.
Here is a link to that discussion

http://groups.google.com/group/medstats/browse_thread/thread/95e098ccc98fdd76?hl=en

Thanks again....everyone...

Marc


*
*   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/

*
*   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/