I have a coefficient plot of the following form:
Code:
sysuse auto
eststo reg_1: reg price mpg
eststo reg_2: reg price mpg headroom
coefplot (reg_1, mcolor(ebblue) msymbol(t) ciopts(color(ebblue yellow red)) level(99 95 90)) (reg_2, mcolor(ebblue) msymbol(s) ciopts(color(ebblue yellow red)) level(99 95 90)), keep(mpg) legend(order(1 "99% CI" 2 "95% CI" 3 "90% CI") rows(1))
Currently the legend explains what each colour is, but I would like to add another legend explaining that the confidence interval with the triangle does not include the "headroom" variable while the confidence interval with the square does include it. Is there a way of adding this second legend? Thank you!
**this post was originally posted on stakc overflow but Nick Cox suggested I post it here**