Y(dependent) = I(0)
X(independent)= I(1)
if I take the first difference of X and make it stationary, is it possible to apply Dumitrescu & Hurlin Causality test. İf the answer is yes, could you please share an article for this situation.
Thanks and regards,
What is the rationale of using D & H? Once panel data are cointegrated, you can just use the coefficient of explanatory variables to explain the dependent variable. If the aim is to test causality, you can test it using any panel causality test.
Mwoya Byaro as you know in order to test causality by D&H it needs the variables have to be stationary at the same level. So I want to know that is it appropriate to make the not stationary variable stationary, by taking the first difference.
Emrah, it is possible to make non stationary to stationary by taking the difference. Failure to do so, it implies spurious regression
I guess I didn't express myself fully. For example, while the Konya causality test can analyze variables at mixed level stationary, the variables for D&H need to be stationary at the same level. Accordingly, as I want to use D&H instead of using Konya causality test, if I make the non-stationary variable stationary by taking its first difference, will this pose a problem in terms of analysis?
- Badges
- Science topic
- Similar topics
- Geoscience
- Asia
- India