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: Mtest Mstat problem |
Date | Fri, 22 Mar 2013 11:39:03 +0000 |
I would set trace on set traced 1 and report where the error occurs. You may need to bump up 1 to 2, 3, etc. to get precise details. Nick On Fri, Mar 22, 2013 at 11:28 AM, James Kirkbride <jbk25@cam.ac.uk> wrote: > Dear all > > I am hoping for advice on an issue I cannot find detailed on the web, on > these archives or in the documentation provided with the mstat & mtest > commands (see http://www.stata-journal.com/article.html?article=st0228) > > I would like to conduct an mtest to determine whether the spatial > distribution of two groups (based on their residential x-y coordinates) > differs. > > I believe I have set-up my data files correctly according to the mtest > documentation, but when I run the mstat command I get an r3301 error message > "3301 subscript invalid". When I run the mtest command I do not get this > error message but the output table does not provide any statistics: > > . mtest, x(oseast1m) y(osnrth1m) g(status) iter(10000) scatter density > > M statistic > Monte Carlo permutation results > H0: The two groups have the same spatial distribution > Number of bins = 20 > Number of permutations = 10000 > > M(obs) c n p=c/n SE(p) [95% Conf. Interval] > > . . . . . . . > > I would be grateful for any help offered on this matter. I have tried > running this in both Stata 11 & 12. Just to say that the graphs produced by > these commands execute successfully. * * 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/