*
*  Example 15.4
*  J. Wooldridge, Econometrics of Cross Section and Panel Data
*
*  Note: The sample data files include all required data transformations.
*        However, in many cases we show how these data transformations would
*        be created in RATS from the basic data, as this is something you will
*        need to know how to do in practice.
*
*
open data keane.raw
data(format=free,org=columns) 1 12723 id numyrs year choice wage educ expwc expbc $
  expser manuf black lwage y81 y82 y83 y84 y85 y86 y87 enroll employ attrit exper expersq
*
set expersq = exper**2
*
* The "status" variable isn't provided in the data set. It's constructed off the
* "choice" variable. choice==1-->status=0 , choice==2-->status=1 ,
* choice>=3-->status=2
*
set status  = %if(choice==1,0.0,%if(choice==2,1.0,%if(choice>=3,2.0,%na)))
*
*  Run this over the 1987 observations with a valid "status"
*
set smpl = y87.and.%valid(status)
*
ddv(type=multinomial,smpl=smpl) status
# educ exper expersq black constant
*
* Test the two experience variables for the home vector. These are the 2nd and 3rd
* parameters.
*
test(zeros)
# 2 3