Hello,
Working on forecasting sales for my business. I have weekly sales data from 01/07/18 to 6/19/22.
I generated a Seasonal ARIMA(0,1,1)(0,1,1) 7 No Intercept model. I am running the code below and am getting the messages. I am new to this and am unsure how to correct to see forecasted values. Thank you.
Warning: | More values of input variable AO104 are needed. |
Warning: | More values of input variable AO153 are needed. |
The value for option LEAD= has been reduced to 0. |
data SalesWeatherWeeklyData10_25_22;
set SalesWeatherWeeklyData10_25_22;
if _N_ = 104 then AO104 = 1; else AO104 = 0;
if _N_ = 153 then AO153 = 1; else AO153 = 0;
run;
PROC ARIMA DATA = SalesWeatherWeeklyData10_25_22 PLOTS=ALL;
IDENTIFY VAR = Sales(1, 7) crosscorr = (AO104(1,7) AO153(1,7));
ESTIMATE p=2 q=(7 ) NOCONSTANT input = (AO104 AO153) METHOD = ML ;
outlier maxnum=20 alpha=0.001;
forecast printall lead=4 out=results1;
RUN;
QUIT;
Hello @kwilz ,
Since your model has input variables, forecasting of the response variable needs values on these input variables. The warning messages indicate that your input data set does not contain the values for these input variables for the future periods when you wanted to obtain forecasts, hence forecast into the future periods cannot be obtained. The following section of PROC ARIMA documentation discusses this when forecasting with input variables:
https://go.documentation.sas.com/doc/en/pgmsascdc/v_032/etsug/etsug_arima_gettingstarted40.htm
Because your input variables are AO dummy variables, you know their future values, so you can simply add values for these inputs in your data set for the length of future periods when you want to compute forecast, and set response variable to missing, then forecasts for these future periods will be computed.
I hope this helps.
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 16. Read more here about why you should contribute and what is in it for you!
Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.
Find more tutorials on the SAS Users YouTube channel.