Forecasting in the absence of precedent

We survey approaches to macroeconomic forecasting during the COVID‐19 pandemic. Due to the unprecedented nature of the episode, there was greater dependence on information outside the econometric model, captured through either adjustments to the model or additional data. The transparency and flexibility of assumptions were especially important for interpreting real‐time forecasts and updating forecasts as new data were observed. We revisit these themes with a time‐varying parameter (TVP) vector autoregression (VAR), which attributes the large jumps primarily to increased volatility rather than changes in the type or propagation of shocks.

Economic forecasting with an agent-based model

We develop the first agent-based model (ABM) that can compete with benchmark VAR and DSGE models in out-of-sample forecasting of macro variables. Our ABM for a small open economy uses micro and macro data from national accounts, sector accounts, input–output tables, government statistics, and census and business demography data. The model incorporates all economic activities as classified by the European System of Accounts (ESA 2010) and includes all economic sectors populated with millions of heterogeneous agents. In addition to being a competitive model framework for forecasts of aggregate variables, the detailed structure of the ABM allows for a breakdown into sector-level forecasts. Using this detailed structure, we demonstrate the ABM by forecasting the medium-run macroeconomic effects of lockdown measures taken in Austria to combat the COVID-19 pandemic. Potential applications of the model include stress-testing and predicting the effects of monetary or fiscal macroeconomic policies. © 2022 The Author(s)

Nowcasting in a pandemic using non-parametric mixed frequency VARs

This paper develops Bayesian econometric methods for posterior inference in non-parametric mixed frequency VARs using additive regression trees. We argue that regression tree models are ideally suited for macroeconomic nowcasting in the face of extreme observations, for instance those produced by the COVID-19 pandemic of 2020. This is due to their flexibility and ability to model outliers. In an application involving four major euro area countries, we find substantial improvements in nowcasting performance relative to a linear mixed frequency VAR. © 2020 The Author(s)

Economic forecasting with an agent-based model

We develop the first agent-based model (ABM) that can compete with benchmark VAR and DSGE models in out-of-sample forecasting of macro variables. Our ABM for a small open economy uses micro and macro data from national accounts, sector accounts, input–output tables, government statistics, and census and business demography data. The model incorporates all economic activities as classified by the European System of Accounts (ESA 2010) and includes all economic sectors populated with millions of heterogeneous agents. In addition to being a competitive model framework for forecasts of aggregate variables, the detailed structure of the ABM allows for a breakdown into sector-level forecasts. Using this detailed structure, we demonstrate the ABM by forecasting the medium-run macroeconomic effects of lockdown measures taken in Austria to combat the COVID-19 pandemic. Potential applications of the model include stress-testing and predicting the effects of monetary or fiscal macroeconomic policies.

Nowcasting Russia’s key macroeconomic variables using machine learning

The article developed a methodology for nowcasting and short-term forecasting key Russian macroeconomic aggregates: real GDP, consumption, investment, export, import, using machine learning methods: boosting, elastic net, and random forest. The set of predictors included indicators of the stock market, money market, surveys, world prices for resources, price indices, and other statistical indicators of different frequency, from daily to quarterly. Our approach makes available a detailed examination of the changes in forecasts with the flow of new information. For most of the considered variables, a monotonic non-deterioration of the forecast quality was obtained with an expansion of available information. Furthermore, machine learning methods have shown significant superiority in predictive performance over naive prediction. The considered methods within the framework of the pseudo-experiment quickly showed a strong drop in real GDP, household consumption, and other variables in the context of the spread of the COVID-19 pandemic in the 2nd and 3rd quarters of 2020. © 2022, Russian Presidental Academy of National Economy and Public Administration. All rights reserved.

Nowcasting domestic demand using a dynamic factor model: the case of Ireland

The COVID-19 pandemic highlighted the need for timely information on the evolving economic impacts of such a crisis. During these periods, there is an increased need to understand the current state of the economy to guide the effective implementation of policy. This is made difficult by the fact that official estimates of economic indicators, such as those published by national statistical agencies, are released with a substantial lag. Using the case of Ireland, this article shows that the information contained in a panel of monthly economic indicators can be related to Quarterly National Accounts under the methodological framework of a dynamic factor model (DFM). The article also suggests that accounting for structural breaks improves the nowcasting performance of domestic demand. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

Forecasting in the absence of precedent

We survey approaches to macroeconomic forecasting during the COVID-19 pandemic. Due to the unprecedented nature of the episode, there was greater dependence on information outside the econometric model, captured through either adjustments to the model or additional data. The transparency and flexibility of assumptions were especially important for interpreting real-time forecasts and updating forecasts as new data were observed. We revisit these themes with a time-varying parameter (TVP) vector autoregression (VAR), which attributes the large jumps primarily to increased volatility rather than changes in the type or propagation of shocks.