*This message was transferred with a trial version of CommuniGate(tm) Pro*
Hi I am using stata to do a frontier anlaysis I wonder if you can healp
solve this simple question and if not refer me to someone else?
,
I have my dependent Variable fo example Life expetancy vs.Independent
variable Public health expenditure , this data is by state for Mexico
So I do in Stata
Frontier Life_exp Pubhealthexp
My question is how do I specify using this Stata command for a control
variable for example percentage of rural population? I assume that
states that have more rural population have less life expectancy.
What I want to run is a model where Life expectancy is explained by
Public health expenditure by state but states that have more rural
population should be treated less hard than those with lower rural
population.
I used the following comand
frontier global pub_perc, uhet( lnpor_rural)
But it seems the effect I get is in the opposite direction I want. WHen
Life expectancy and public health expenditure is the same for 2 states,
the state that has a higher rural population is penalized more than the
one that has less rural population.
If I do a simple regression between Life expectancy and rural
population, the higher the rural population the lower the life expectancy.
Thanks for your help,
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/