Announcement

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

  • Measuring vertical segregation

    Dear All,

    I'm trying to find a way to measure ordinal occupational segregation between males and females.

    I think the Stata command for this is the user-written -rankseg-? If, suppose I have an ordered occupational categorical variable, with 1 being the lowest rank and henceforth the rank goes upwards, should the command look something like this:

    rankseg occ_order, h r u(female)

    Or is there any other way to measure it?

    Thank you in advance.

  • #2
    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. Explain what you want in general arithmetic or statistics terms - most of us are not from your area so exactly what ordinal occupation segregation means is not clear.

    Strictly from the description in the documentation, It appears the user-written procedure rankseg does this. However, there are almost certainly other ways to calculate this construct (see how it is calculated in various papers in your discipline). If you let us know what you need to calculate and what your data look like, it is likely someone can help you.

    Comment


    • #3
      Originally posted by Phil Bromiley View Post
      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. Explain what you want in general arithmetic or statistics terms - most of us are not from your area so exactly what ordinal occupation segregation means is not clear.

      Strictly from the description in the documentation, It appears the user-written procedure rankseg does this. However, there are almost certainly other ways to calculate this construct (see how it is calculated in various papers in your discipline). If you let us know what you need to calculate and what your data look like, it is likely someone can help you.
      Hello, thank you for the reply.

      I contacted the author and he said the command should be used for multiple groups, and I had only two. So I am not using this command in the case at hand.
      Last edited by Alina Faruk; 21 Jun 2019, 18:45.

      Comment


      • #4
        You may wish to try the user-written nldecompose, since it supports ologit and oprobit models.
        Best regards,

        Marcos

        Comment


        • #5
          Originally posted by Marcos Almeida View Post
          You may wish to try the user-written nldecompose, since it supports ologit and oprobit models.
          Thank you for the suggestion!

          Comment

          Working...
          X