[Arash Sereshki]

Another simplier method:

sysuse auto,clear

mfp: regress mpg weight displacement if foreign==0
fracplot displacement

mfp: regress mpg weight displacement if foreign==1
fracpred dfit, for(displacement)
fracpred ds, for(displacement) s

gen low=dfit-1.96*ds
gen high=dfit+1.96*ds

addplot: rarea low hi displacement ,color(gs14%80) sort || ///
line dfit displacement ,color(red)|| ///
scatter mpg displacement if foreign==1,sort

Thanks @ Raymond Zhang
I was wondering if you could inform me whether it is possible to replace the scatter plot in the last part of your command (scatter mpg displacement if foreign==1,sort) with a Component-plus-residual plot. The reason for this is I have multiple independent variables in MFP and the scatter plot does not take into account the effect of the other independent variables in the model.
This is what I did base on your commands:

mfp: regress mpg weight displacement if foreign==0
fracplot displacement
mfp, center(no): regress mpg weight displacement if foreign==1
fracpred dfit, for(displacement)
fracpred ds, for(displacement) s
gen low=dfit-1.96*ds
gen high=dfit+1.96*ds
addplot: rarea low hi displacement ,color(gs14%80) sort || line dfit displacement ,color(red) || cprplot displacement if foreign==1,sort
The STATA's output is an error indicating that "cprplot is not a twoway plot type".
Also, although I did not centerized the independent variables in the regression model, the Y axis shows value in the compontnt-plus residual value.'
Please let me know what you think. Thank you

[Marcela Vieira]

Hi everyone,

I have generated three time-series graphs, using the following code:

tsline p10 if timesteps<21
graph save p10, replace

tsline p50 if timesteps<21
graph save p50, replace

tsline p90 if timesteps<21
graph save p90, replace

graph combine p10.gph p50.gph p90.gph, note("10th percentile" "50th percentile" "90th percentile")



However, I want to overlay instead of combining them (and also change the colour). I tried some of the code above but had no success, could anyone please help me?

Thank you,