Not a tough one, but I must be missing something. Thanks. An analyst wants to model quarterly sales data using an autoregressive model. She has found that an AR(1) model with a seasonal lag has significant slope coefficients. She also finds that when the second and third lags are added to the model, all slope coefficients are significant too. Based on this, the best model to use would most likely be an: A) AR(1). B) AR(4). C) AR(2).
Isn’t it AR(1) ?
No its an AR(4)… makes no sense right??? Is it just a bad Q? I’ve seen a couple of duds in schweser’s Q bank.
AR(4) Seasonal lag means you add value from last year. See “Seasonality in TIme-series models” section in the book.
elcfa Wrote: ------------------------------------------------------- > AR(4) > Seasonal lag means you add value from last year. > See “Seasonality in TIme-series models” section in > the book. I get that you add a value from last year, I just don’t see why its an AR(4).
its on a set of quarterly data. so you start with the ar(1), add lags 2 and 3 because of the significance, and then add lag 4 because 4 quarters gets you back to the same quarter in the previous year. leaving you with an ar(4)