Scatter plot with *adjusted* line of best fit

[Lise Lovland]

Hi there,

I am trying to create a scatter plot of IV and DV, where the line of best fit is adjusted for one (binary) covariate (IV2).

My regression model is simple ( regress DV IV1 IV2 ), and I suspect the answer might be simple too, but so far no luck..

Would anyone be able to help?

Thanks,
Lise

[Andrew Musau]

A scatter plot is a two-dimensional figure. With a binary 0/1 x variable and a continuous y variable, you will have markers at x=0 and x=1. I am not sure what you have in mind and how your regression with two variables is relevant to your question.

[Nick Cox]

I don't know what you mean by adjustment, but one flavour would be just that in your case

\regress DV IV1 i.IV2

defines two regression lines, one for each state of IV2.

I'd caution against the abbreviations DV and IV as just tribal jargon. Why it's unlikely that anyone here will interpret DV as Deo volente it's entirely possible that some people here regard IV as meaning instrumental variable.

regplot from the Stata Journal can handle this. The article at https://www.stata-journal.com/articl...article=gr0009 explains the principle but install the software from gr0009_1. You can get a clickable link from

search regplot

SJ-10-1 gr0009_1 . . . . Software update for model diagnostic graph commands
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . N. J. Cox
(help anovaplot, indexplot, modeldiag, ofrtplot, ovfplot,
qfrplot, racplot, rdplot, regplot, rhetplot, rvfplot2,
rvlrplot, rvpplot2 if installed)
Q1/10 SJ 10(1):164
provides new command rbinplot for plotting means or medians
of residuals by bins; provides new options for smoothing
using restricted cubic splines; updates anova examples

SJ-4-4 gr0009 . . . . . . . . . . Speaking Stata: Graphing model diagnostics
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . N. J. Cox
(help anovaplot, indexplot, modeldiag, ofrtplot, ovfplot,
qfrplot, racplot, rdplot, regplot, rhetplot, rvfplot2,
rvlrplot, rvpplot2 if installed)
Q4/04 SJ 4(4):449--475
plotting diagnostic information calculated from residuals
and fitted values from regression models with continuous
responses

You give no data example, contrary to our request, but this is an example you can run once you have installed regplot.

sysuse auto, clear 
gen gpm = 100/mpg
regress gpm weight i.foreign
label var gpm "Gallons per 1000 miles"
regplot, sep(foreign) fitopts(lc(orange blue)) ms(Oh +) mc(orange blue) legend(pos(11) ring(0) col(1) order(4 3))

[Lise Lovland]

Ah brilliant - thank you very much !! I will refer to the guidelines for posting new questions next time. Again, thanks!

[Nick Cox]

The backslash in the first code statement in #3 was a typo and should please be ignored.