The have you tried working with -margins- and -marginsplot- after fitting your model? I would check that out as a possibility first.
HTH,
Billy
Sent from my iPhone
On Jan 23, 2013, at 2:37, James Bernard <jamesstatalist@gmail.com> wrote:
> Hi all,
>
> I am struggling with plotting main effect and interaction effect of my
> negative-binomial model... I though Stata might have something, given
> the popularity of these plots among empiricists
>
>
>
> This is a a fixed effect negative binomial model.... I have pace as my
> main ID, Pace-squared, then an interaction term "Scale" and then
> interaction of that variable with Pace and Pace-Squared.
>
>
> I want to draw this where my DV is on the vertical axis and main plot
> on the X and then interaction on Y (like a surface plot). I wonder if
> this can be done in Stata, given that negative binomial is a nonlinear
> model....
>
>
> ----------------------------------------------------------------------------------------
> lagpatent_f1 | Coef. Std. Err. z P>|z|
> [95% Conf. Interval]
> -----------------------+----------------------------------------------------------------
> Pace | 1.494223 .5783452 2.58 0.010
> .3606869 2.627758
> Pace^2 | -.6852545 .2394282 -2.86 0.004
> -1.154525 -.2159839
> Scale | .0563032 .3031137 0.19 0.853
> -.5377887 .650395
> Pace*Scale | -1.551876 .8982472 -1.73 0.084
> -3.312408 .2086566
> Pace*Scale^2 | .849984 .4441609 1.91 0.056
> -.0205553 1.720523
>
> _cons | .5746716 .2601009 2.21 0.027
> .0648832 1.08446
>
>
> Many Thanks,
> james
> *
> * 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/
