Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Radoslaw Panczak <r.panczak@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: Why do the stcox CI differ when using margins? |
| Date | Mon, 25 Feb 2013 16:38:07 +0100 |
Maarten, Nick, Thank you for your input. Differences are not large indeed so if there is no other way I might have to resort to default strategy of margins & marginsplot. Best, r On 25 February 2013 16:05, Nick Cox <njcoxstata@gmail.com> wrote: > As Maarten implies, if inspection shows that -margins- gives similar > intervals to -stcox- then the graph produced by -marginsplot- may be > adequate for your purposes I think you'd have a hard time explaining > symmetric intervals and -- especially- negative bounds otherwise, or > in any case. > > Nick > * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/