Statalist


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

st: re: statsby slowness


From   David Airey <david.airey@Vanderbilt.Edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: re: statsby slowness
Date   Tue, 14 Aug 2007 07:02:48 -0500

"E. Paul Wileyto" <epw@mail.med.upenn.edu> replied:


For large numbers of "by groups," I have found it works better/ faster to write my own script that repeatedly pulls the original file from a tempfile, and then uses a keep statment to restrict the analysis. Statsby spends too much time looking to see who is in.

I'll do that. Cheers. Gene microarray data have stupidly large numbers of by groups these days. Offlist, Michael Blasnik rote that the official statsby incorporated his speed improvements already, so the speed is what it is for the spearman command. Other commands are much faster (like regress). Since my posts, I've found the ranking the data and running corr speeds considerably. Also running statsby on subsets of the data and appending results is faster.

--
David C. Airey, Ph.D.
Research Assistant Professor

*
* 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