Working Paper: CEPR ID: DP16496
Authors: Massimiliano Marcellino; Todd Clark; Andrea Carriero
Abstract: This paper focuses on nowcasts of tail risk to GDP growth, with a potentially wide array of monthly and weekly information used to produce nowcasts on a weekly basis. We consider different models, consisting of Bayesian mixed frequency regressions with stochastic volatility, Bayesian quantile regressions, and Bayesian partial quantile regression, the last of which incorporates data reduction through a common factor. Our results show that, within some limits, more information helps the accuracy of nowcasts of tail risk to GDP growth. Accuracy typically improves as time moves forward within a quarter, making additional data available, with monthly data more important to accuracy than weekly data. Accuracy also typically improves with the use of financial indicators in addition to a base set of macroeconomic indicators.
Keywords: forecasting; downside risk; pandemics; big data; mixed frequency quantile regression
JEL Codes: C53; E17; E37; F47
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| More information (Y50) | Accuracy of nowcasts of tail risk to GDP growth (E37) |
| Monthly data (Y10) | Accuracy of nowcasts of tail risk to GDP growth (E37) |
| Inclusion of financial indicators (C43) | Accuracy of nowcasts of tail risk to GDP growth (E37) |
| Bayesian regression models (C11) | Accuracy of nowcasts of tail risk to GDP growth (E37) |