2
$\begingroup$

What precisely are the differences between rolling, recursive and fixed window regression?

As far as I understand,

  • recursive: we train on a period $y(0)$ to $y(n)$ then predict $\hat{y}(n+1)$. Then we train on $y(0)$ to $y(n+1)$ and predict $\hat{y}(n+2)$ and so forth. The window we train on gets bigger, and we do one-step ahead predictions.

  • rolling: we train on a period $y(0)$ to $y(n)$ then predict $\hat{y}(n+1)$. Then we train on $y(1)$ to $y(n+1)$ and predict $\hat{y}(n+2)$ and so forth. The size of the window we train on stays the same size, and we do one-step ahead predictions.

  • fixed: here is where I am confused. I was thinking that fixed was that we train on $y(0)$ to $y(n)$, then predict $\hat{y}(n+1)$ to $\hat{y}(n+m)$. But i have the feeling that this is actually multi-step forecasting. I also find some sources on the internet that claim that rolling and fixed are the same. I am confused... Is rolling different from fixed? If yes how?

Some conflicting/confusing sources:

I am relatively confused at this point and I am very happy for any answers explaining the difference or pointing me towards some relevant sources...


Update

I found a source giving some explanantion:

Source:

Regression-Based Tests of Predictive Ability, Kenneth D. West and Michael W. McCracken, https://www.jstor.org/stable/2527340?seq=3#metadata_info_tab_contents

enter image description here enter image description here

However I'm still somewhat confused between multi-step ahead forecasting and fixed windows...

$\endgroup$

1 Answer 1

4
$\begingroup$

Your definitions are correct. Economic Forecastsing - Elliot and Timmerman (2016) is a good ref for that. See the image therein:

enter image description here

However I'm still somewhat confused between multi-step ahead forecasting and fixed windows..

Recursive (expanding windows), rolling windows and fixed windows, deal with parameters estimation. Multi-step forecasting is another problem. You can make one step ahead or multi step ahead forecasts with any of the three estimation procedure you mention.

$\endgroup$
2
  • $\begingroup$ I quickly looked through the book but could not find any explanation of the window types on first sight, I would appreciate the precise page numbers if possible, Thanks! $\endgroup$
    – charelf
    Commented May 23, 2021 at 11:34
  • 1
    $\begingroup$ I have done even more. $\endgroup$
    – markowitz
    Commented May 23, 2021 at 12:26

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.