Announcement

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

  • Generate a fixed effects panel dataset given specific variance-covariance matrix

    I am looking for an easy way to simulate panel data for a given variance-covariance matrix assuming the underlying data generating process is that of a fixed effects panel. In particular, I want to have control over:

    (a) the correlation between the fixed effects and the independent variables
    (b) the correlation between the independent variables.

    The usual corr2data and drawnorm is unable to take care of it since it does not allow for the fixed effects to be the same for a given panel

  • #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 of a routine to do what you want. I suppose you can set up the variables yourself and search for the parameters that give the correlations you want.

    Comment


    • #3
      Thank you for the tips and I have been able to figure it out - it's a very annoying amount of algebra but it worked out well.

      Comment

      Working...
      X