Announcement

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

  • After having run a robust regression, do I still need to test for heteroskedasticity?

    "regress indep dep control control vce(robust)"
    After the regression, Stata doesn't allow me to use the command "estat hettest"

    estat hettest
    hettest not appropriate after robust cluster()


    Would there be another test you recommend or should be done after this?

  • #2
    As your standard errors are robust to heteroscedasticity, you won't worry about it.

    Comment


    • #3
      As others have pointed out, robust standard errors are not a remedy that fix all problems. You probably want to compare robust and regular SEs. https://gking.harvard.edu/publicatio...hey-do-not-fix
      Best wishes

      Stata 18.0 MP | ORCID | Google Scholar

      Comment

      Working...
      X