Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Daniel Marcelino <dmsilva.br@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: Date: Thu, 7 Apr 2011 16:20:17 -0400 |
| Date | Thu, 7 Apr 2011 18:59:15 -0300 |
Luisa, maybe I misunderstood part of your inquire. However, some words can help you think more specific about your outcome. First, yes you should interpret your coefficient as you do in a linear regression. Regard that the main difference between both techniques is the shrinkage and liability aspects, not the coefficient or slope interpretation. Second, as I understood from your question a more accurate model of change might be the trajectory over time from identity variation. Daniel On Thu, Apr 7, 2011 at 5:20 PM, Luisa Soares-Miranda <luisasoaresmiranda@gmail.com> wrote: > Dear All, > > I have one doubt and I think you can help me. I am a Phd student and I have conducted one mix-model analysis using the command xtmixed to analyze associations over 3 years of data. so I have xi: xtmixed .... || codigo: i.year, covariance(identity). So my question is can I interpret the coefficient as I interpret it in a linear regression? For example if I increase one unit in my exposure the outcome will change Coef. over time? Or I should only say that exposure and outcome are associated and in each direction, over time. > > thank you so much > regards > > Luisa > * > * 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/ > -- About me: http://danielmarcelino.zip.net/ * * 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/