I am trying to check if my Auto Regressive Distributed Lag (ARDL) model provides stable estimates over time. I am not sure if I should be using a recursive or rolling window method. I know that the recursive method anchors the starting point and continually adds one time period whereas the rolling window sets a fixed window of time and rolls up one observation at a time. However, I do not know when each method is more appropriate. Can you tell me why I would choose one over the other? Also if I estimated both and found that the estimates are stable over time for both models, what would be the difference between each finding?
$\begingroup$
$\endgroup$
Add a comment
|