nep-for New Economics Papers
on Forecasting
Issue of 2021‒05‒17
three papers chosen by
Rob J Hyndman
Monash University

  1. Combining Bayesian VARs with survey density forecasts: does it pay off? By Bańbura, Marta; Brenna, Federica; Paredes, Joan; Ravazzolo, Francesco
  2. Macroeconomic Forecasting in Poland: Lessons From the COVID-19 Outbreak. By Rybacki, Jakub; Gniazdowski, Michał
  3. Nowcasting Macroeconomic Aggregates in Argentina: Comparing the predictive ability of different models By Emilio Blanco; Laura D’Amato; Fiorella Dogliolo; Lorena Garegnani

  1. By: Bańbura, Marta; Brenna, Federica; Paredes, Joan; Ravazzolo, Francesco
    Abstract: This paper studies how to combine real-time forecasts from a broad range of Bayesian vector autoregression (BVAR) specifications and survey forecasts by optimally exploiting their properties. To do that, it compares the forecasting performance of optimal pooling and tilting techniques, including survey forecasts for predicting euro area inflation and GDP growth at medium-term forecast horizons using both univariate and multivariate forecasting metrics. Results show that the Survey of Professional Forecasters (SPF) provides good point forecast performance, but also that SPF forecasts perform poorly in terms of densities for all variables and horizons. Accordingly, when the model combination or the individual models are tilted to SPF's first moments, point accuracy and calibration improve, whereas they worsen when SPF's second moments are included. We conclude that judgement incorporated in survey forecasts can considerably increase model forecasts accuracy, however, the way and the extent to which it is incorporated matters. JEL Classification: C11, C32, C53, E27, E37
    Keywords: Entropic tilting, Judgement, Optimal Pooling, Real Time, Survey of Professional Forecasters
    Date: 2021–05
  2. By: Rybacki, Jakub; Gniazdowski, Michał
    Abstract: The aim of this paper is to analyze the forecast errors of Polish professional forecasters under the COVID-19 crisis in 2020—based on the Parkiet competition. This analysis shows that after the initial disruption related to imposed lockdown in March and April, commercial economists were capable of lowering their forecasts errors of the industrial production and retail sales. On the other hand, the far worse performance has been seen in the case of the market variable; either the size of errors or the disagreement were elevated throughout the entirety of 2020. Furthermore, long-term forecasts that were produced during the first year of the pandemic have been characterized with visible inconsistencies (i.e., projections of economic growth were similar when forecasters either assumed a strong increase in unemployment or when they did not).
    Keywords: GDP forecasting, Labor Market forecasts, COVID-19
    JEL: E27 E32 E37
    Date: 2021–05–11
  3. By: Emilio Blanco; Laura D’Amato; Fiorella Dogliolo; Lorena Garegnani
    Abstract: Monetary policy making requires a correct and timely assessment of current macroeconomic conditions. While the main source of macroeconomic data is quarterly National Accounts, of- ten published with a significant lag, higher frequency business cycle indicators are increasingly available. Taking this into account, central banks have adopted nowcasting as a useful tool for having an immediate and more accurate perception of economic conditions. In this paper, we extend the use of nowcasting tools to produce early indicators of the evolution of two components of aggregate domestic demand: consumption and investment. The exercise uses a broad and restricted set of indicators to construct di↵erent dynamic factor models, as well as a pooling of models in the case of investment. Finally, we compare di↵erent approaches in a pseudo-real time out-of-sample exercise and evaluate their predictive performance.
    Keywords: Nowcasting, dynamic factor models, forecast pooling
    JEL: C22 C53 E37
    Date: 2020–11

This nep-for issue is ©2021 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.