Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | harryxgordon <michellev.tran@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: logit - which "obs not used"? |
Date | Mon, 5 Mar 2012 12:28:28 -0800 (PST) |
Dear Statalist, I have a do-file that loops through hundreds of different logit regressions based on different stratification schemes for my full dataset. Each time I run a logit regression, observations are dropped because certain variables predict the data perfectly. I am wondering if Stata stores the final dataset (i.e. the dataset without the "obs not used") that the logit regression is run on, and if so, how I can access this. I need to weed out certain regression results based on the number of observations with certain characteristics in each regression sample. It seems that my only alternative, which would be considerably more time-consuming, would be to read the log-file which would say something like, "note: var1 != 0 predicts success perfectly var1 dropped and 22 obs not used", go back to my full dataset, drop var1 manually, and then look at the data. Any suggestions as to how I could avoid this would be greatly appreciated. Thank you, Michelle Tran Research Analyst -- View this message in context: http://statalist.1588530.n2.nabble.com/logit-which-obs-not-used-tp7346268p7346268.html Sent from the Statalist mailing list archive at Nabble.com. * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/