Is it valid to use the Bai-Perron method to detect breaks in the constant and and the trend in a regression, and to use the break dates for cointegration with structural break?

  • $\begingroup$ What happened to your previous user account? Looks like you got yourself a new one. $\endgroup$ Mar 20 '17 at 9:28
  • $\begingroup$ As far as I remember, the model for Bai-Perron needs to be stationary (apart from the tested breaks). This would rule out subsequent cointegration analysis. There are also methods for directly addressing cointegration with trend breaks. $\endgroup$
    – Sven S.
    Jun 20 '17 at 10:46
  • $\begingroup$ @LarsAhnland, if you still have access to your other account, what do you think of my answers to your questions here and here? $\endgroup$ Dec 13 '18 at 13:54

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.