Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Suryadipta Roy <sroy2138@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: Interpretation of interaction term in log linear (non linear) model |
| Date | Mon, 10 Jun 2013 13:48:53 -0400 |
Dear David, The dependent variable in my regression is indeed a continuous variable, highly skewed with a lot of zeros (bilateral imports between countries). I will refrain from using an odds ratio interpretation as you have suggested. Here is a link to Maarten's Stata tip # 87: http://www.maartenbuis.nl/publications/interactions.pdf Best regards, Suryadipta. On Mon, Jun 10, 2013 at 1:34 PM, David Hoaglin <dchoaglin@gmail.com> wrote: > Dear Suryadipta, > > I'll have to look at Maarten's Stata tip #87. > > In the piece by Michael Rosenfeld the counts in the log-linear model > come from a 2x2 table, which is the usual setting for an odds ratio. > He also says, "all other factors held constant." That's the part of > the common interpretation of regression coefficients that I urge > people to avoid, because it does not reflect the way regression > actually works. > > Lecture 10 by Sharyn O'Halloran deals with multinomial data, which can > be the basis for odds ratios (relative to a reference category). It > also has the problem of oversimplifying the interpretation by saying > "with the other variables in the model held constant." It saddens me > to see that flawed interpretation being given to students. It will > probably lead them to make mistakes later on. > > If Trade in your model is "continuous," I do not see a basis for odds ratios. > > David Hoaglin > > On Mon, Jun 10, 2013 at 1:02 PM, Suryadipta Roy <sroy2138@gmail.com> wrote: >> Dear David, >> >> Thank you so much for the insightful comments! I have tried to be very >> careful with -margins- and -marginsplot- to derive conclusions about >> predictions and marginal effects. As regards the log-odds >> interpretation, I was under the impression that interactions in a >> broad category of non-linear models with multiplicative effects (e.g. >> poisson, nbreg, log-linear, etc) can be given a log-odds >> interpretation. My impressions are based on the readings of Maarten >> Buis's Stata tip # 87: Interpretation of interactions in non-linear >> models) as well as the following link: >> http://www.stanford.edu/~mrosenfe/soc_388_notes/soc_388_2002/Interpreting%20the%20coefficients%20of%20loglinear%20models.pdf >> >> I believe that I should have been more careful about the "odds ratio >> remaining constant" statement. I completely understand that it would >> change for interaction terms when any one of the associated variables >> changes. However, I was wondering if things will be different in the >> absence of interactions as stated here in this link (on pp. 8): >> http://www.columbia.edu/~so33/SusDev/Lecture_10.pdf >> I will change some of my variables to check for the effects on the >> odds ratio. Once gain, thank you very much for the help! >> >> Sincerely, >> Suryadipta. > * > * 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/ * * 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/