Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Maarten buis <maartenbuis@yahoo.co.uk> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: AW: Missing F statistics. |
Date | Tue, 22 Jun 2010 06:10:42 -0700 (PDT) |
--- On Tue, 22/6/10, natasha agarwal wrote: > But in situations where there are no other way to define > the clusters and hence the number of constrains are more > than the number of clusters, can one still report with > the results obtained with the missing F value? You are obviously in trouble, but that is normal in empirical research. Unfortunately reality has the nasty habbit of not conforming to our models. The real questions is are your troubles so large that you need to be worried. You seem to have a general idea about what the problems are, so it is now up to you to make a judgement call. I gave you a way that may help with that yesterday: http://www.stata.com/statalist/archive/2010-06/msg01191.html Remember we know nothing about your data, how it was collected, your research question, what is considered important in your (sub-)discipline, etc. All these tend to be important when making the final judgement call whether or not it is wise to use one technique or the other. All we can do is give you some general advise like the one I have given you above. -- Maarten -------------------------- Maarten L. Buis Institut fuer Soziologie Universitaet Tuebingen Wilhelmstrasse 36 72074 Tuebingen Germany http://www.maartenbuis.nl -------------------------- * * 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/