I'm new to SAS and I was doing some forecasting in SAS Forecast Studio on sales data and was trying to figure out the difference between these two options:
Model Select -> Use holdout sample for model selection
Forecast -> Calculate statistics of fit over an out-of-sample range
It's my understanding that in using a holdout it does things in this order:
1) remove holdout from sample
2) calculate statistics of fit for multiple models
3) choose best model
4) re-introduce holdout data
5) calculate statistics of fit over all data
With the "Calculate statistics of fit over an out-of-sample range" option can someone explain to me how this process is different?