Dear Stata Users,
I am computing a multinomial logit and its predicted probabilities - command margins- as follows:
I am using marginsplot (mplotoffset for being precise) to graph the predicted probabilities with specific values of employ2.
Outcome 0 ("continuing coh") has a much higher predicted probability than the other two. Is there the possibility
of introducing a second axis for outcome 0 and then allow a smoother comparison of trends for each outcome?
Thank you very much.
- Lydia
I am computing a multinomial logit and its predicted probabilities - command margins- as follows:
PHP Code:
svy: mlogit uniontype2 i.durationtype i.employ2 , level(90) rrr base
PHP Code:
margins, level(90) pr(out(1)) pr(out(2)) pr(out(0)) vsquish vce(unconditional) force atmeans post at(employ2=(1(1)4))
PHP Code:
mplotoffset , xdim(_outcome) legend( label(1 "E/E") label(2 "M/U,F/E") label(3 "M/E,F/U") label(4 "M/U,F/U") size(small) ring(5) symxsize(*0.5) row(2)) ytitle("Probability", height(10)) title("Employment (a)") offset(.1) recast(scatter) plotregion(lcol(black)) xlab(,labsize(small) ) xtitle("") plot2opts(msymbol(D) fcol(black) fintensity(30)) plot1opts( fcol(black) fintensity(15) ) ci2opts(recast(rcap)) ci1opts(recast(rcap) ) plot3opts(msymbol(T) fcol(black) fintensity(50)) plot4opts(msymbol(S) fcol(black) fintensity(70)) xlab(1 "Continuing coh" 2 "Dissolution" 3"Marriage", labsize(medsmall)) ci4opts(recast(rcap) ) ci3opts(recast(rcap) ) ylab(0(.1)1)
Outcome 0 ("continuing coh") has a much higher predicted probability than the other two. Is there the possibility
Thank you very much.
- Lydia
Attached Files
