Working Paper: CEPR ID: DP10160
Authors: Davide Pettenuzzo; Allan G. Timmermann; Rossen Valkanov
Abstract: We propose a new approach to predictive density modeling that allows for MIDAS effects in both the first and second moments of the outcome and develop Gibbs sampling methods for Bayesian estimation in the presence of stochastic volatility dynamics. When applied to quarterly U.S. GDP growth data, we find strong evidence that models that feature MIDAS terms in the conditional volatility generate more accurate forecasts than conventional benchmarks. Finally, we find that forecast combination methods such as the optimal predictive pool of Geweke and Amisano (2011) produce consistent gains in out-of-sample predictive performance.
Keywords: Bayesian estimation; GDP growth; MIDAS regressions; out-of-sample forecasts; stochastic volatility
JEL Codes: C11; C32; C53; E37
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| high-frequency financial variables (C58) | conditional mean of GDP growth (E20) |
| high-frequency financial variables (C58) | conditional volatility of GDP growth (O49) |
| conditional volatility of GDP growth (O49) | more accurate forecasts (C53) |
| MIDAS effects (C22) | predictive accuracy (C52) |
| forecast combination methods (C53) | out-of-sample predictive performance (C52) |
| MIDAS effects during high volatility (C58) | larger gains in predictive accuracy (C52) |
| MIDAS effects during stable periods (E32) | more pronounced first moment effects (E70) |