Dear all,

I am trying to compare the performance of organisations.

I have already used the DEA (Data envelopment analysis in STATA) to identify the performance scores of the organisations.

I would like to use quantile regression to subdivide this scores in different levels (0.5, 0.25, 0.50, 0.75 and 0.95) with performance scores as the response variable.

Without using this code in STATA.

gen quartile=.

                                               

 levels dmu, local(levels)

foreach k of local levels{

centile eff1, centile(5 25 50 75 95)

replace quartile=1 if eff1<=r(c_1) & dmu==`k'

replace quartile=2 if eff1>r(c_1) & eff1<=r(c_2)  & dmu==`k'

replace quartile=3 if eff1>r(c_2) & eff1<=r(c_3)  & dmu==`k'

replace quartile=4 if eff1>r(c_3)  & eff1<=r(c_4) & dmu==`k'

replace quantile=5 if eff1>r(c_4) & dmu==`k'

Nb. eff1 is the performance score obtained after running the DEA model.

 dmu is the symbol have used to identify the organisations I would like to compare their prices.

Regards,

Nancy.

You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.