Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Probit model with sample selection and binary endogenous variable

    Hi

    I am trying to estimate the following model.
    Y1= aX1 + bX2+ E.
    Y1 is a binary variable.
    X2 is also a binary variable.
    X2 is endogenous.
    I also have a sample selection problem.
    Y1 is the employment status in 2011 for all those who are already employed in 2005. Y1 is a binary variable, it takes value 1 if a person is employed in 2011 and takes value 0 if a person is not employed in 2011.

    My query:
    I am not able to figure out how to build this model in stata.
    The commands that I have come across so far:
    ivregress: I cannot use it as my dependent variable is binary.
    ivprobit: I cannot use it as my endogenous variable is binary, IVPROBIT assumes that the endogenous variable is continuous.
    If I use the heckprobit command, It would take care of the sample selection problem. But how do I correct for endogenity with sample selection.
    Is there any other command that I am not aware of in this discussion.


    Thank you
Working...
X