topic Re: time series in SAS Forecasting and Econometrics

time series

bara — Fri, 03 Jul 2020 11:06:05 GMT

Hi!

How can I interpret the seasonal ARIMA Model (0,1,1)(1,0,0)[12] ?

Re: time series

dw_sas — Mon, 06 Jul 2020 18:43:39 GMT

Hi @bara ,

The model, ARIMA(0,1,1)(1,0,0)12, represents a seasonal ARIMA model with a:

first non-seasonal difference,
first-order non-seasonal moving average term, and
first-order seasonal autoregressive term.

The seasonal index for your model is 12, which is typically used for monthly time series.

In general, ARIMA models are described as: ARIMA(p,d,q)(P,D,Q)s. The lowercase p, d, q represent the non-seasonal autoregressive (p), differencing (d), and moving average (q) orders, respectively. The uppercase P, D, Q represent the seasonal autoregressive (P), differencing (D) and moving average (Q) orders, respectively.

For additional details about the mathematical model and notation for ARIMA models, please see the following link in the PROC ARIMA documentation:

https://go.documentation.sas.com/?docsetId=etsug&docsetTarget=etsug_arima_gettingstarted13.htm&docsetVersion=15.1&locale=en

I hope this helps!

Re: time series

bara — Sat, 11 Jul 2020 13:16:55 GMT

@dw_sas thanks,

p=1 in the non seasonal ARIMA part indicates that the current observations of the series are correlated with themselves at lag 1

what is mean if P=1 in the seasonal ARIMA part ?

Re: time series

solarflare — Mon, 13 Jul 2020 13:49:34 GMT

The P=1 for the seasonal part of the model means that the current observation is correlated with themselves at lag = number of periods in the season.

For example, if you are using monthly data then the current observation is correlated to itself at lag = 12.

Likewise, if you are using quarterly data, then the auto-correlation would be at lag = 4.