MCA/ Joint CA: Combining scatterplot of observations with mcaplot

[Nadine Bast]

Dear Statalist,

this is a very reduced version of a much larger dataset:

* Example generated by -dataex-. To install: ssc install dataex
clear
input float id byte(f1 o3 o4 s1)
  1 1 1 0 0
  2 1 0 0 0
  3 1 0 0 0
  4 1 0 0 0
  5 1 0 0 0
  6 1 0 0 0
  7 1 0 0 0
  8 1 1 1 0
  9 1 0 0 0
 10 1 1 0 0
 11 1 1 1 1
 12 1 1 1 0
 13 1 1 1 0
 14 1 0 0 0
 15 1 0 0 0
 16 1 0 0 0
 17 1 0 0 0
 18 1 0 1 1
 19 1 0 0 0
 20 1 1 1 0
 21 1 0 0 0
 22 1 0 0 0
 23 1 0 0 0
 24 1 0 0 0
 25 1 1 0 0
 26 1 0 1 0
 27 1 0 1 0
 28 1 0 0 1
 29 1 0 1 0
 30 1 0 0 0
 31 1 0 0 0
 32 1 0 1 0
 33 1 1 1 0
 34 1 0 0 0
 35 1 1 1 0
 36 1 1 1 0
 37 1 0 0 0
 38 1 0 1 1
 39 1 0 0 0
 40 1 1 0 0
 41 1 1 1 0
 42 1 0 1 1
 43 1 0 0 0
 44 1 0 0 0
 45 1 1 0 0
 46 1 0 1 0
 47 1 0 0 0
 48 1 1 0 0
 49 1 1 1 0
 50 1 0 1 1
 51 1 1 1 0
 52 1 0 0 0
 53 1 0 1 0
 54 1 0 0 1
 55 1 1 1 0
 56 1 1 0 1
 57 1 0 0 1
 58 1 0 0 0
 59 1 1 0 1
 60 1 1 1 0
 61 1 0 1 1
 62 1 0 1 1
 63 1 1 0 1
 64 1 1 1 0
 65 1 1 1 1
 66 1 1 0 1
 67 1 1 1 0
 68 1 0 1 0
 69 1 1 1 1
 70 1 0 0 0
 71 1 1 0 0
 72 1 0 0 0
 73 1 0 0 0
 74 1 0 1 0
 75 1 0 0 0
 76 1 1 1 0
 77 1 0 0 0
 78 1 1 1 0
 79 1 1 0 0
 80 1 1 1 1
 81 1 1 0 0
 82 1 1 0 0
 83 1 0 1 0
 84 1 1 1 0
 85 1 1 1 0
 86 1 1 1 0
 87 1 0 0 0
 88 1 1 1 0
 89 1 0 0 0
 90 1 0 0 0
 91 1 1 0 1
 92 1 1 1 0
 93 1 1 0 0
 94 1 0 0 0
 95 1 1 0 1
 96 1 0 0 0
 97 1 0 1 0
 98 1 1 0 1
 99 1 0 0 0
100 1 0 0 0
end
label values f1 f1ex
label def f1ex 1 "vg", modify
label values o3 o3
label def o3 0 "nf", modify
label def o3 1 "f", modify
label values o4 o4
label def o4 0 "nm", modify
label def o4 1 "m", modify
label values s1 s1
label def s1 0 "nnaS", modify
label def s1 1 "natS", modify

I am performing joint correspondence analysis and visualise the results with mcaplot...

mca o3 o4 s1, supp(f1) method(joint)
mcaplot, overlay  xline(0) yline(0) scale(.5) aspectratio(1) legend(off) mlabpos(12) msymbol(circle) mlabgap(2) name(mca)

and a space of individuals / scatterplot of the observations:

predict a1 a2
scatter a2 a1,  xline(0) yline(0) scale(.3) mlabel(id) name(scat)

(it looks much less strange on my original dataset, I promise).

What I would like to do now is to combine both graphs so that I have both the variables and observations in one plot, similar to what can be done with the factoextra package in R.
But, e.g.

graph combine mca scat

gives me two seperate graphs.

Is it even possible to combine mca postestimation plots with a scatterplot?

Best,
Nadine

[Andrew Musau]

The mcaplot is itself a kind of scatter plot, so I don't know how that would work having another scatter plot overlaid. There may be a direct solution which I am not aware of, but here is a way to reconstruct the graph using twoway.

https://www.statalist.org/forums/for...raph-after-mca

[Nadine Bast]

Thank you, Andrew!
I think I found a solution, I can enter the Case ID as a supplementary Variable to obtain the cloud of individuals. I am not yet sure the result is the same, though.