Is it possible to compare in-sample and out-of-sample forecasts by calculating a MSPE for each? For example, my in sample period is say 12/1987-12/2015, and my out-of-sample forecasting period is 12/1993-12/2015 (I use an expanding window to forecast, with a burn-in period of 5 years to determine the initial parameters). Can I compare these two by taking the in-sample MSPE from 12/1993-12/2015, and compare that to out-of-sample? Or does this not even make sense? I want to see how my out-of-sample works compared to what my in-sample says, but I have no idea how this would look for an expanding window forecast, since it converges to the in-sample result eventually.