SARIMA Model equation

[gonzalo espineira]

Hello everyone,

I am currently using ARIMA and SARIMA models to forecast a company´s sales. I get the general idea of the models, but i cannot seem to understand the exact equation stata uses to predict the model´s output.
My dataset is comprised of 120 monthly observations of sales "altom" and the command i use to model the sales is the following:

arima d.altom, noconstant ar(1) ma(1) mar(1, 12) mma(1, 12)
predict model

What i want stata to tell me is the equation it uses with the command "predict" after running the model.
I looked at the stata manual but all the examples there aim to model the difference of the seasonality, as if the command was:
arima ds12.altom, noconstant ar(1) ma(1) mar(1, 12) mma(1, 12)

Thanks everyone in advance!

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

I don't understand your problem - it looks like you're running a model very similar to the first example in Forecasting after ARIMA. Stata in the sense of the package itself won't "tell you" how it calculates things - that is done in the documentation. Often, it helps to replicate and work through the examples in the documentation.

[gonzalo espineira]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

I don't understand your problem - it looks like you're running a model very similar to the first example in Forecasting after ARIMA. Stata in the sense of the package itself won't "tell you" how it calculates things - that is done in the documentation. Often, it helps to replicate and work through the examples in the documentation.

Thanks for your response Phil. Yeah, i missed reading the FAQ on how to properly ask questions, my bad.
My problem is not exactly "a problem", but i cannot seem to find what exactly the equation stated by the model is.
My guess is the following:
(Yt-Yt-1)=b1*(Yt-1-Yt-2)+b12,1*(Yt-12-Yt-13)-b1*b12,1*(Yt-13-Yt-14)+Et+d1*Et-1+d12,1*Et-12+d1*d12,1*Et-13
b1-> AR(1) coefficient
b12,1-> MAR(1,12) coefficient
d1-> MA(1) coefficient
d12,1-> MA(1,12) coefficient.
Is there anywhere i can check whether my equation is correct?

Thanks