Add histogram of values distribution when graphing conditional marginal effects?

[Stephen Long]

Hi all,

I am learning about graphing the marginal effects of a variable conditional on the values of a second variable. I see how to use the margins command and then graph those results with confidence intervals, which gives me a sense of whether the marginal effects of one variable in the interaction are significant over the value range of the other variable in the interaction. But, my conditioning variable has a range of 0 to 85, with a mean of less than 3. I would like to show a histogram of that distribution overlaid on top of the marginal effects graph. I see that in R, there is a package called "interplot" that makes it easy. Does anyone know how to do the same thing in Stata? I'm on version 15 if that matters.

Here is what I have been doing:

logit dependentvariable variableA variableB c.variableA#c.variableB covariateC covariate D, cluster(yadayada)
margins, dydx(variableA) at(variableB=(0(5)85)) vsquish
marginsplot, ylin(0)

Thanks so much for any tips.

[David Radwin]

I have never tried the program overlay (below), but you might see if it works for your purpose.

Alternatively, you could use graph combine to place histogram(s) outside the main plot like https://www.stata.com/includes/contimages/combine5.gif .

. ssc describe overlay

-----------------------------------------------------------------------------------------------------------------------------------
package overlay from http://fmwww.bc.edu/repec/bocode/o
-----------------------------------------------------------------------------------------------------------------------------------

TITLE
      'OVERLAY': module to overlay multiple x vs y graphs

DESCRIPTION/AUTHOR(S)
      
      This command allows the user to overlap the same graph BY a
      variable.  Hence it is possible to produce individual profiles
      simply including patient as the by  variable. You can overlay
      kernel densities, histograms and just about any graphing
      function. However to get the best results the graph function
      needs to have an xlab() and ylab()  otherwise for the final plot
      there is no way of putting the same graphs on the same axes.
      This is an enhanced version of the command published in STB-54 as
      gr43.
      
      Distribution-Date: 20020423
      
      Author: Adrian Mander , GSK
      Support: email [email protected]
      

INSTALLATION FILES                              (type net install overlay)
      overlay.ado
      overlay.hlp
-----------------------------------------------------------------------------------------------------------------------------------
(type ssc install overlay to install)