Abstract
This paper provides consistent information criteria for the selection of forecasting models which use a subset of both the idiosyncratic and common factor components of a big dataset. This hybrid model approach has been explored by recent empirical studies to relax the strictness of pure factor-augmented model approximations, but no formal model selection procedures have been developed. The main difference to previous factor-augmented model selection procedures is that we must account for estimation error in the idiosyncratic component as well as the factors. Our main contribution is to show the conditions required for selection consistency of a class of information criteria which reflect this additional source of estimation error. We show that existing factor-augmented model selection criteria are inconsistent in circumstances where N is of larger order than root-T, where N and T are the cross-section and time series dimensions of the dataset respectively, and that the standard BIC is inconsistent regardless of the relationship between N and T. We therefore propose a new set of information criteria which guarantee selection consistency in the presence of estimated idiosyncratic components. The properties of these new criteria are explored through a Monte Carlo simulation study. The paper concludes with an empirical application to long-horizon exchange rate forecasting using a recently proposed model with country-specific idiosyncratic components from a panel of global exchange rates.
Original language | English |
---|---|
Pages (from-to) | 1087–1106 |
Number of pages | 20 |
Journal | Journal of Applied Econometrics |
Volume | 32 |
Issue number | 6 |
Early online date | 9 Apr 2017 |
DOIs | |
Publication status | Published - Sep 2017 |
Keywords
- Forecasting
- Factor model
- model selection
- information criteria
- idiosyncratic