Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Negative binomial regression (nbreg): Plot an interaction effect of two continuous/interval variables


From   jhilbe@aol.com
To   statalist@hsphsun2.harvard.edu
Subject   RE: st: Negative binomial regression (nbreg): Plot an interaction effect of two continuous/interval variables
Date   Sun, 11 Sep 2011 13:29:09 -0400 (EDT)

I have 10 page Appendix on constructing and interpreting interactions for count models in my recent book, "Negative Binomial Regression, 2nd edition" (2011, Cambridge University Press) and a complete 53 page chapter on constructing, graphing, and interpreting interactions for logistic models in my "Logistic Regression Models" (2009, Chapman & Hall/CRC). I use Long and Freese's methods, and others, for graphing.

If you would like, I'll send you a PDF of the Appendix on Interactions and include a separate secton from the LRM book on constructing a graph for this type of interaction. All of the code for constructing interactions and graphics in both Stata and R is made available in both books. Let me know by sending me an email at --hilbe@asu.edu-- and I'll get it off to you.

Joseph Hilbe

-------------------------------------------------------------------------
-------------------------------------------------------
Hilbe, Joseph M (2011), Negative Binomial Regression, 2nd edition, Cambridge University Press
     http://www.stata.com/bookstore/nbr.html
Hilbe, Joseph M (2009), Logistic Regression Models, Chapman & Hall/CRC
     http://www.stata.com/bookstore/lrm.html
Hardin, JW and JM Hilbe (2003), Generalized Estimating Equations, Chapman & Hall/CRC
     http://www.stata-press.com/books/gee.html
Hardin, JW and JM Hilbe (2007), Generalized Linear Models and Extensions, 2nd ed, Stata Press
     http://www.stata-press.com/books/glmext.html
Muenchen, RA and JM Hilbe (2010), R for Stata Users, Springer
http://www.springer.com/statistics/computanional+statistics/book/978-1-4419-1317-3
-------------------------------------------------------------------------
--------------------------------------------------------



Date: Sat, 10 Sep 2011 12:06:27 -0400
From: Cameron McIntosh <cnm100@hotmail.com>
Subject: RE: st: Negative binomial regression (nbreg): Plot an interaction
effect of two continuous/interval variables

Fred,

I don't know if -1SD and +1SD are always the best values to use. I would recommend also trying a range of more "interesting/meaningful" values of your moderator to generate predicted probabilities for plotting. You should also take a look at these papers:

Buis, M.L. (2010). Stata tip 87: Interpretation of interactions in non-linear models. The Stata Journal, 10(2), 305-308.

Norton, E.C., Wang, H., & Ai, C. (2004). Computing interaction effects and standard errors in logit and probit models. The Stata Joumal, 4(2), 154-167.http://www.unc.edu/~enorton/NortonWangAi.pdf

Ai, C., & Norton, E. C. (2003). Interaction terms in logit and probit models. Economic Letters, 80, 123-129.

Hayes, A.F., & Matthes, J. (2009). Computational procedures for probing
interactions in OLS and logistic regression: SPSS and SAS implementations. Behavior Research Methods, 41, 924-936.?http://www.personal.psu.edu/jxb14/M554/articles/Hayes&Matthes200
9.pdf

Francoeur, R.B. (2011). Interpreting interactions of ordinal or continuous variables in moderated regression using the zero slope comparison: tutorial, new extensions, and cancer symptom applications.International Journal of Society
Systems Science, 3(1/2), 137-158.

Cam

Date: Sat, 10 Sep 2011 17:35:53 +0200
Subject: st: Negative binomial regression (nbreg): Plot an
interaction effect
of two continuous/interval variables
From: statalistrequest@googlemail.com
To: statalist@hsphsun2.harvard.edu

Dear users of statalist,

I have a nbreg model containing 3 continuous variables and one
interaction
effect of two of these variables.

How can I get a judicious plot of the interaction effect? A common
method
for plotting interactions effets in general is a graph, where one uses
predications for -SD Mean +SD of both variables.

How can I do that or another valuable plot in stata for nbreg? Or how
can I
use prvalue to calculate the needed values to put these data somehow
in excel?







*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index