I have estimated a regression and found a breakpoint using chow:

enter image description here

Then I created a dummy variable which is 0 before the break and 1 from the break until the end. This is the result:

enter image description here

I was assuming this p-value for the dummy variable means the break is not relevant. Is this correct?

I then interacted the variable with the other independent variables:

enter image description here

One of the interactions is very significant.

I don't know what to conclude from it. Is this break relevant and I should segment my regression or not?

If it makes any difference: These are financial returns of a company as dependent upon a stock index returns and usd exchange rates, all as log.


Your Answer

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

Browse other questions tagged or ask your own question.