1
$\begingroup$

I recently came by a post that states in panel data with small time dimensions the stationarity issue is not present, is this true? can anybody provide a source for this?

  • I'm working with a panel data set for 10 states over 11 years, with variables: unemployment, poverty rates, age controls in (%) and minimum wages.

Should I bother trying to test for unit roots? if so what tests would you recommend? I am using R and having difficulties trying to find and understand some tests used in panel data sets.

-thanks

$\endgroup$
  • $\begingroup$ What is your time dimension? Are your observations yearly? $\endgroup$ – Alecos Papadopoulos Nov 20 '17 at 20:57
  • $\begingroup$ Should of stated that, yes, yearly (from 2000-2010 to be specific). $\endgroup$ – Cole Nov 20 '17 at 21:04
1
$\begingroup$

The data sample is so small that formal testing for stationarity would be essentially worthless. Inspect visually your individual series for any obvious trend. This would be the case where even with a short sample non-stationarity would be a problem.

$\endgroup$
  • $\begingroup$ Thank you for your reply, I will look for any noticeable trends in the data, if so i will probably run the regression in first differences. $\endgroup$ – Cole Nov 20 '17 at 21:21

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.