October 3, 2008

Evaluating CPB's published GDP growth forecasts; a comparison with individual and pooled VAR based forecasts

We compare the accuracy of our published GDP growth forecasts from our large macro model, SAFFIER, to those produced by VAR based models using both classical and Bayesian estimation techniques.

We employ a data driven methodology for selecting variables to include in our VAR models and we find that a randomly selected classical VAR model performs worse in most cases than the Bayesian equivalent, which performs worse than our published forecasts in most cases. However, when we pool forecasts across many VARs we can produce more accurate forecasts than we published. A review of the literature suggests that forecast accuracy is likely irrelevant for the non-forecasting activities the model is used for at CPB because they are fundamentally different activities.

Contacts

Photo of Adam Elbourne
Adam Elbourne +31 6 11627514 Read more
Photo of Henk Kranendonk
Henk Kranendonk +31 6 21977303 Read more
Photo of Rob Luginbuhl
Rob Luginbuhl +31 6 11301400 Read more
Photo of Bert Smid
Bert Smid +31 6 11594311 Read more
Martin Vromans Read more

Read more about