8.23: Seasonal ARIMA (SARIMA) models in R

[@DrobbinsMpharm]

Thank you, Dr Arif. Very good, and to the point. Many thanks from Wales.

[@Nader95]

didn't know about the auto.arima function in r , thanks!

[@dontgiveafluck]

Great tutorial, thanks!

[@tinacrocker4477]

Outstanding tutorial thanks.

[@matheuscastro271]

thank you. very good lecture.

[@berespinosa559]

I've a question. Video mentions that p and P are set to 0 because of the statistically significant spike in the ACF at lags 1 and 4. But the PACF has significant spikes at those same sites, which I thought would be a signal to set q and Q to 0. Is there prioritization going on, or how is this explained?

[@deepblueocean5055]

Thanks you so much!

[@flaviomacaubastorres]

Hello, can you explain why did you use lag = 4 in the seasonal difference?

[@nishatsikder]

lag=4 for quarterly data.

[@maven12LA]

THANK YOU

[@zeyneptekir6341]

Hi, the nsdiff= 0 what should we do? Should we continue with arima model or sarima ?

[@DrImranArif]

It means that you do not need to take a seasonal difference to make your time-series (seasonal) stationary. You probably need to watch all videos in the chapter to get more ideas. The choice between ARIMA and SARIMA depends on the lags (seasonal lags).

[@michaelogolla9350]

Hello, the ndiffs () does not work in my version of R nor is the ggtsdisplay function. What should I do in this case. I believe there should be a way for these functions to work. Kindly advise.

[@lexandour5823]

Hello, I have the same problem. Did you find a way to fix it ?

[@nagarjunsubburaj6139]

@@lexandour5823 Install and load the package "forecast"

[@kevineotieno5]

It would be more helpful if you could provide the dataset. Thanks

[@jillou31]

hi, can you send me a script please , thinks in advanced