>
>
Tim seems to be asking how to grab the 90th percentile after imputations are run or variables
are created in a way where that 90 percentile point is not consistent each time the do-file is run.
One way to do this is to use -sum, d- with the saved scalars for the percentiles, ex:
*--------begin
clear
sysuse auto
sum price, d
di "`r(p10)'" //10 percentile
di "`r(p90)'" //90 percentile
gen dummy = 1 if inrange(price,`r(p10)', `r(p90)')
recode dummy (.=0)
tab price dummy
*---------end
~ Eric
__
Eric A. Booth
Public Policy Research Institute
Texas A&M University
[email protected]
Office: +979.845.6754
Fax: +979.845.0249
http://ppri.tamu.edu
On Jan 25, 2010, at 4:50 PM, Tim Malacarne wrote:
> Hello,
>
> Does anyone know how to create a dummy variable based on percentile ranges of a multiply imputed variable using Stata 11? I have imputed income and want to create dummies representing ranges of the income distribution for each imputation, but I've been unable to find a way to vary the cut points with for the different imputations.
>
> I can use "mi passive: generate dummy if inc>x & inc<y" to create dummies in each imputation, but as each imputation has a different value for its 90 %, this isn't ideal.
>
> Thanks a lot,
> Tim
>
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
