Announcement

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

  • RMSE with asreg in rolling window regression

    I have recently found and been using “asreg” command for Stata. I find it incredibly useful. I am having trouble completing one task and wonder if someone might be able to shed some light on how to achieve this with asreg. I have a dynamic panel data set with multiple individuals over multiple years. I am trying to run both year specific (relatively easy) and person specific regressions (rolling over the prior 10 year period). Both of which are easily achievable using asreg. The trouble I am having is that I would like to capture the RMSE of each of these regressions. While I can save the residual of the latest observation in the window, I cannot figure out how to either save all residuals or how to save the RMSE. Any suggestions on how this might be possible?


  • #2
    An rmse option is documented in the help for asreg (SSC, as you are asked to explain). If that isn't the answer, you will need help from the author.

    Comment


    • #3
      Version 2.1 of asreg ( you can check on Stata command line by typing which asreg ) reports RMSE. For example,

      Code:
      webuse grunfeld
      bys company: asreg invest mvalue kstock, w(year 10) rmse
      Therefore, your query is not clear to me whether your version does not report RMSE or you cannot find RMSE for two different types of regressions. In case the latter is true, then you can rename variables created by the first regression. e.g.
      Code:
      ren _* _reg*

      and then run another regression.
      Regards
      --------------------------------------------------
      Attaullah Shah, PhD.
      Professor of Finance, Institute of Management Sciences Peshawar, Pakistan
      FinTechProfessor.com
      https://asdocx.com
      Check out my asdoc program, which sends outputs to MS Word.
      For more flexibility, consider using asdocx which can send Stata outputs to MS Word, Excel, LaTeX, or HTML.

      Comment


      • #4
        Thank you so much! I had an older version of asreg. This is a great program, thank you again.

        Comment

        Working...
        X