BIS paper proposes simplified tests for predictive densities
A new working paper from the Bank for International Settlements (BIS) proposes a simplified framework for evaluating conditional predictive densities. The approach accommodates various estimation schemes and enables researchers to apply widely used tests in settings where their validity was previously uncertain.
Bridging theoretical and empirical gaps
The paper provides an alternative set of assumptions under which existing tests for predictive densities remain valid.
This framework abstracts from parameter estimation uncertainty and specific estimation schemes, accommodating both rolling and expanding window estimation, as well as stationary and non-stationary processes.
A novel aspect is the consideration of weighted test statistics, allowing researchers to focus on specific parts of the predictive distribution, such as the left tail, without completely disregarding other regions.
Stochastic volatility for US production forecasts
Through Monte Carlo simulations, the authors demonstrate that their proposed tests exhibit favorable size and power properties under the new assumptions.
In an empirical application forecasting US industrial production, the study finds that incorporating stochastic volatility into an unobserved components model is essential.
This ensures correctly calibrated density forecasts for US industrial production growth at both monthly and quarterly frequencies, highlighting the practical importance of the framework.