1
$\begingroup$

I have an auto.arima model output with ARIMA(000)(110)[4] with sigma^2=0.005, so I assume the model fits well the data. But I'm trying to understand the model itself... If I did all the maths correctly, the change at time t depends on the change at the same time in 2 previous years, being expressed as:

xt = (α1+1) xt-4 - α1xt-8 + wt.

Is it correct?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

That's right. Assuming you don't have a constant in the model, and using your notation, then the model with one seasonal difference and one seasonal AR term is

$(1 - \alpha_1 L^4)(1 - L^4)x_t = \epsilon_t$

which is

$x_t - \alpha_1 x_{t-4} - x_{t-4} + \alpha_1 x_{t-8} = \epsilon_t$

or, as you wrote,

$x_t = (1 + \alpha_1)x_{t-4} - \alpha_1 x_{t-8} + \epsilon_t$

Improve this answer
$\endgroup$

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.