Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: exceeded memory limit


From   rgates@stata.com (Richard Gates)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: exceeded memory limit
Date   Wed, 16 Aug 2006 14:01:11 -0500

B. Water <barleywater@hotmail.com> is trying to get Fishers exact
test to run on a 2x10 table with N = 1575.  

> 
> no. of obs 1575 2 var's: var1 had 2 categories and var2 had 10 categories.
> 
> i tried:
> 
> .tabulate var1 var2, exact
> 
> and get this: 
> 
> "i've omitted the tabulation output"
> 
> exceeded memory limits using exact(1); try again with larger #; see help tabulate for details
> r(911);

Clearly this is too large of a problem for -tabulate, exact- to handle.  With
such a large N, I am sure the chi-squared p-values are valid.  If you go
beyond exact(5), you've gone too far.

We made an update to -tabulate, exact- in version 9 (Jan. 20 2006) where we
gained some efficiency in the computation.  We also added an enumeration log so
the user can see how big the problem is and whether a solution is feasible.
Judging by the size of N for your problem it still may not complete, but if you
want to send me your table I can see how it does.

-Rich
rgates@stata.com
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index