Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Nils Braakmann <nilsbraakmann@googlemail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Clustering Standard Errors. |
Date | Mon, 14 Jun 2010 16:39:04 +0200 |
Hi Natasha, intuitively, I would cluster the errors on the region-industry-level as this is the level where your variable varies. Depending on what you are trying to do, you could either use twoway clustering or first generate a cluster variable with -egen clustervar = group(region industry)- and then using this. Best, Nils On Mon, Jun 14, 2010 at 3:50 PM, natasha agarwal <agarwana2@googlemail.com> wrote: > Dear Everyone, > > I have a variable (FDI) which is defined as the FDI in an industry in a region. > > At what level is it correct to cluster the standard errors? > > Thanks > Natasha > * > * 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/ > * * 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/