1
$\begingroup$

Say you have two variables with trends in them. It is often said that this leads to spurious regression. My question is, when will regression with ARIMA error (which may involve differencing) eliminate this problem and when instead do you have to look at issues of cointegration, for example the cointegration in ARDL or ECM models. Can you ever use regression with ARIMA error if the variables are cointegrated? Can you ever use regression with ARIMA error if the variables are integrated of different orders.

$\endgroup$

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.