According to Forecasting: Principles and Practice

Seasonality is always of a fixed and known frequency.

If it is a fixed and known frequency, does that mean every series with monthly or quarterly data can use methods that captures seasonality?

I am asking because I am not sure if I could use SARIMA and Holt-Winters with my monthly data because there seems to be no seasonal pattern based on my ACF plot. But I've seen some papers have D=0 in their SARIMA model.

  • $\begingroup$ There is absolutely no problem with D=0 in a seasonal model. $\endgroup$ Dec 30, 2022 at 14:32
  • $\begingroup$ Does that mean I could use SARIMA or Holt-Winter's even my series do not show seasonal patterns? @RichardHardy $\endgroup$
    – arl-txt
    Dec 30, 2022 at 14:45
  • $\begingroup$ If there is no "S", you get ARIMA. $\endgroup$ Dec 30, 2022 at 16:25
  • $\begingroup$ Detail: The method name honours Peter Ross Winters, hence always Winters, not Winter's. trinityfuneralhome.ca/obituary/peter-ross-winters $\endgroup$
    – Nick Cox
    Jan 3 at 11:10

1 Answer 1


No, this doesn't mean that seasonality applies to every series with monthly or quarterly data. Monthly or quarterly is just the interval at which data is being collected; it does not necessarily imply seasonality. It's simply saying that if there is seasonality in your data, its frequency will not change over your data set.

If you are not detecting seasonality, then you probably shouldn't be using a model intended for seasonality, though it might be a good exercise to run different models, some with a seasonality component and some without, and compare them using some criterion. Even comparing SARIMA to Holt-Winters would be a good exercise.


Your Answer

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

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