Announcement

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

  • SE of wage-elasticity of labor supply

    Hello,
    I would like to measure the standard error of the wage-elasticity of labor supply which is a function of wage-elasticity of separation to employment and to non-employment.
    First, I estimate the wage-elasticity of separation to employment by performing a logit model on the probability of separation to employment, the elasticity is then obtained from the "margins dyex" command.
    Second, I estimate the wage-elasticity of separation to non-employment by performing a logit model on the probability of separation to non-employment, the elasticity is then obtained from the "margins dyex" command.

    The idea is then to store the estimates so that I can run "lincom" command to measure the wage-elasticity of labor supply. I can store the estimates but I get an error message when I try to "suest" the estimates. Since the SE of wage-elasticity of separation are obtianed using the delta method, I cannot use the suest command. I am wondering whether there is another command that allows for nonstandard VCE?

    Thanks!

  • #2
    You didn't get a quick answer. You'll increase your chances of a helpful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

    I don't know if this is legit for logit, but sometimes you can trick Stata into running two models at the same time by stacking the data and then creating two values of each variable with zeros in half the data. By zeroing out values for half the data, the estimates should be very similar to what you get when you run them separately.

    Comment

    Working...
    X