Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Nick Cox <njcoxstata@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: How to find extreme values |
| Date | Tue, 27 Mar 2012 09:54:33 +0100 |
Since outliers have a big effect on means and standard deviations this is usually a poor method. Nick On Tue, Mar 27, 2012 at 9:42 AM, San K <devank@gmail.com> wrote: > I normally calculate the standard deviation and mean. Then you can > define what your extreme points are. For example, you can see anything > < (mean-4*SD) or > (mean + 4*SD) is an extreme value. > > I don't know Stata code much but in SPSS you can simply calculate the > mean & SD by aggregation command without really aggregating your data > set. Hope you can do similar. On Tue, Mar 27, 2012 at 1:20 PM, Sandy Y. Zhu <sandy.zhu@yale.edu> wrote: >> I was wondering if anyone knows how to find outliers or extreme values >> in Stata? I have a data whose values mostly lie in (-1,1) range, but >> some of them are really far off due to the way the data is scaled >> (somewhere around +/-100000). Is there any chance I can eliminate >> those with a stata function? >> >> Thank you! >> >> -- >> Yours sincerely, >> >> Sandy Y. Zhu >> * >> * 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/ * * 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/