Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "JVerkuilen (Gmail)" <jvverkuilen@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: positive interaction - negative covariance |
Date | Fri, 22 Feb 2013 13:10:27 -0500 |
On Fri, Feb 22, 2013 at 12:32 PM, andrea pedrazzani <andrea.pedrazzani.piter@gmail.com> wrote: > Also, both b1 and the combined coefficient (b1+b3) are positive, but > the covariance between b1 and b3 is negative. It sounds strange to > me... This kind of thing is all too common in practice with interactions, which are often soaking up some often unimportant nonlinearity. This can be created by the nature of the dependent variable, if there is ceiling or floor effect, for instance, or a bit of skew. I concur with Nick that graphing will be very helpful. * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/