I am trying hard to complete my TS student project and I am stuck on something and I have read through everything I can find, but still cant figure this out.

I have fit my TS data of 42 data points to an AR(1) and AR(2) using linear regression, and I have taken 1st differences of my correlogram in order to fit an ARIMA.

My question is how do I calculate the Box-Pierce Q Stat at the different lags for each of my fit models?

I have calculated it for the raw data using the macro, but I don't know how to do it for the fit models.

Any help or pointing in the right direction would be greatly appreciated.

[NEAS: Compute the residuals using each model.]

Please disregard last post. I was being dense. I figured this out.