I am planning to do a regression of a time series y with an exogenous variable x, I have multiple time series which are considered to be modeled by one model (coming from the same process, [y1, x1],[y2, x2],...[yn, xn] total n time series). I would like to fit one ARMAX model (or regression with ARMA error) for them. However, I don't find a way to do that in R and Python. (I know this can be achieved in Matlab).

I came across this answer Estimating same model over multiple time series. But this is for ARIMA model without endogenous variable, and it requires padding data with Nan while still maintain the seasonality. Is there any simple way like using merge to merge different experiments and then fit in Matlab?



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.