Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | James Bernard <jamesstatalist@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: esttab |
Date | Thu, 2 May 2013 22:07:19 +0800 |
Thanks Rebecca, by p() I meant the precision level at which Stata would assign the stars. But since p-values are calculated at 3-digit level, then it really does not matter if I declare this I want the beta at 3-digit level, se (that is, I don't want t- ratios) also at 3-digit precision level and I want stata to show a sign for <0.1 level of significance (using the dagger sign or + here) How can I accommodate these in -esttab? Thanks, James On Thu, May 2, 2013 at 9:45 PM, Rebecca Pope <rebecca.a.pope@gmail.com> wrote: > James, > I'm confused by p(3). Did you mean se(3) since you are requesting the > standard errors? Or do you want to see p-values and significance > stars? > > If (3) was misstyped, you shouldn't have any trouble with > esttab m1, b(3) se(3) star(+ 0.1 * 0.05 ** 0.01 *** 0.001) > > However, if you want to see standard errors and p-values, -esttab- > won't accomodate you. It only allows 2 lines per cell. > > -esttab- is just a wrapper for -estout- though. You have the option to > request standard errors and p-values from -estout-. > estout m1, cells(b(fmt(%12.3fc) star) se(fmt(%12.3fc)) p(fmt(%4.3f))) > starlevels(+ 0.1 * 0.05 ** 0.01 *** 0.001) > > You'll obviously need to adjust the name of your model (m1) and the > format of b and se to accomodate your data. > > Please note that -estout-, of which -esttab- and -eststo- are > components, is a user-written program and you are asked to cite such > programs when you post. > > For others, -estout-, by Ben Jann, is available from SSC. > > Regards, > Rebecca > > On Thu, May 2, 2013 at 8:15 AM, James Bernard <jamesstatalist@gmail.com> wrote: >> Hi all, >> >> I have been trying to use eststo and esttab. The problem is that I am >> trying to do a few simultaneous changes to the way the output is >> displayed. >> >> 1- showing S.E. instead of t ratio >> >> 2- significance display by using -star(+ 0.1 * 0.05 ** 0.01 *** 0.001) >> >> 3- limiting the number of digits to 3 by using b(3) and p(3) >> >> but, the command does not accommodate these options together: [ only >> one allowed of z, se, p, ci, and aux()] >> >> How can I impose all of these changes simultaneously? >> >> Thanks, >> James >> * >> * 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/ > * > * 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/ * * 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/