Say I have an ARIMA model that I have fit and with with I want to make forecasts/predictions.
Say the model is an ARIMA(2,0,2) with some seasonality (1,0,0,365)
Since p and q are 2, we are relying on two periods of prior data.
Say my (training + test) set have 100 observations. Say I want to forecast/predict 20 observations out of sample.
Does the model start with observation 99 to predict observation 101 (the first out of sample prediction/forecast) and likewise predicted/forecasted observation 118 and 119 be used to predict/forecast observation 120 if I don't have a dynamic model in place?
Thanks in advance.