Announcement

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

  • Cross Sectional Dependence XTCD and XTCSD

    Hi Everyone,

    Iam using CS-ARDL and CS-DL approaches. I already have estimated these approaches. However, I wanted to estimate CD test for each model specifications. I have used the following commands:


    xtpmg d.dy d.dp dybar dpbar ldybar ldpbar l2dybar l2dpbar l3dybar l3dpbar , lr(l.dy dp) replace mg

    predict residuals

    xtcd residuals or pmg.........However, it did not work.................Any suggestions please.

    Regards,
    Marwan



  • #2
    Try
    Code:
    xtpmg d.dy d.dp dybar dpbar ldybar ldpbar l2dybar l2dpbar l3dybar l3dpbar , lr(l.dy dp) replace mg
    
    predict residuals
    
    xtcd residuals, resid
    xtcdf residuals
    xtcd2 residuals, noest

    Comment


    • #3
      Hi Jesse,

      I have tried these codes. They did not work. Eberhardt developed the following code for MG group effect to test the CD

      xtmg ly ltr llive lf ln, trend robust res(mg_res)

      xtcd mg_res, resid


      However, Iam looking for PMG effect

      Comment


      • #4
        They did not work.
        This tells us absolutely nothing. You have to be more specific. Do the commands not work? What error messages are you getting? Are the commands not doing what you want them to do? Can you provide a data example? Etc.

        Comment


        • #5
          The commands do work.....But, it can not control for the CD test. Eberhardt developed the code for the MG , which as follows:


          Compute the residuals from a heterogeneous parameter production function using the Pesaran & Smith (1995) Mean Group estimator (xtmg if installed) with a country-specific linear trend. Then test the residuals for cross-section independence .
          xtmg ly ltr llive lf ln, trend robust res(mg_res)
          .xtcd mg_res, resid



          These codes work very well and control the CD test. However, they are only used for MG rather than PMG. I am looking for PMG.

          Comment


          • #6
            The xtcd/... commands don't really care which model you used, as long as you feed them a variable of residuals. So I don't see how they fail to work after xtpmg? Or are you saying you don't manage to predict the residuals after xtpmg?

            Comment


            • #7
              Yes

              Comment


              • #8
                I don't know how to get the residuals after xtpmg. Google might have answers?

                Comment


                • #9
                  Yes, do you have answer for this ???.............That is the problem .......

                  Comment

                  Working...
                  X