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" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: ldecomp question |
Date | Mon, 27 May 2013 13:16:23 +0100 |
This was posted successfully on Friday: http://www.stata.com/statalist/archive/2013-05/msg00757.html To see whether a post got through, please look at the list archives. On the face of it your error is clearly signalled by -ldecomp-. Your -at()- option is illegal, as it contains three elements and none contains a scalar value. If I understand this correctly an option of the form at(foo 42; bar 24) would be legal. I guess you didn't get a reply because people were surprised that you were puzzled. Nick njcoxstata@gmail.com On 27 May 2013 12:40, Alberto R Osella <arosella@irccsdebellis.it> wrote: > Sorry I'm forwarding again this question because it came back to me (I don't > know why) > > Dear Statalist, > I'm using -ldecomp- from ssc (updated yesterday) on W7 (Stata 12.1) and I > get an error when I use the option at(). > My code is as follow: > ldecomp dep_var, direct(Var_1) indirect(Var_2) at (Var_3 1; Var_4 2; > Var_5_3) > and the error is the following: > each element in the at() option must contain of two elements > the first element is one of the control variables and the second element its > value > an error occurred when bootstrap executed _ldecomp > r(198); * * 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/