Announcement

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

  • Suggestion on Hausman Test Reported Results

    The literatures that I follow for my study always reports HAUSMAN test in the results table. According to my knowledge, Durbin-Wu-Hausman test is done to check endogeny presence and there is another Hausman Test to check of fixed or random effect model is required. However, the literatures do not clearly says which test value is reported here. If has any advice would highly appreciated.

    Click image for larger version

Name:	Screen Shot 2565-05-22 at 15.36.44.png
Views:	1
Size:	77.5 KB
ID:	1665746


  • #2
    Farhan:
    this is something difficult to advise on.
    From your table, isìt seems that OLS and instrumental variable regression were compared.
    In addition, it seems that Authors refer to cross-sectional instead of panel data regerssions.
    Kind regards,
    Carlo
    (Stata 19.0)

    Comment


    • #3
      Carlo Lazzaro Thank you Carlo for your insights.

      I have a follow up question. Reading the documentation of ivendog I found it is to be run for Durbin-Wu-Hausman tests after the regression but when I use the command after regression its gives me error as below. This is equivalent to running "estat endog" after Stata's native command "ivregress". Initially my understanding is this is due to "xt" command

      Code:
      . ivendog
      ivendog works only after ivreg, ivreg2; use dmexogxt after xtivreg
      last estimates not found
      r(301);
      Based on my study, I need to check for endogeny by Durbin-Wu-Hausman test.

      I ran the ivendog after both these regressions but it gives me same error

      Code:
      xtivreg REM_PROXY_w POST_REG  INBD ROA_w Size MTB_x_w LEV_w NOA_X_w (ABS_DA_w = C_PROD_w) i.Year, fe vce(
      > robust) first small
      Code:
       xi:xtivreg2 REM_PROXY_w POST_REG INBD ROA_w Size MTB_x_w LEV_w NOA_X_w (ABS_DA_w = C_PROD_w) i.Year, firs
      > t fe robust endog(ABS_DA_w)
      Below I have attached a note from ivendog for reference

      ivendog is for use after ivreg or ivreg2; see help ivreg or help ivreg2 (if installed). The test is not valid with pweights, nor with the robust or cluster options of the
      original estimator, and will not be performed in these circumstances.

      Example

      . ivreg lwage (exper educ = motheduc fatheduc huseduc)
      ivendog
      ivendog exper
      It would kind of you if you could provide your insight if any. Thank you in advance

      Comment


      • #4
        Farhan:
        did you abibe by the following?
        Code:
        ivendog is for use after ivreg or ivreg2; see help ivreg or help ivreg2 (if installed).
        Kind regards,
        Carlo
        (Stata 19.0)

        Comment


        • #5
          Carlo Lazzaro Yes, Carlo exactly in my case I believe I will not be able to use this as my command is xtivreg or xtivreg2. However, I am wandering if there is any way around I could do to perform the Durbin-Wu-Hausman test.

          Comment

          Working...
          X