I have the following time-series that I need to model using SARIMA. There is a clear seasonality pattern but there is no apparent trend.

Should I de-seasonalize (seasonal differencing) my time series before applying SARIMA?

GDP Growth Rate

  • $\begingroup$ If you are happy with my answers please accept them to bring notoriety. $\endgroup$
    – IrishStat
    Mar 16, 2020 at 20:03

1 Answer 1


no .. because seasonal structure is the S in SARIMA . If you post an example of your data I may be able to help further


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.