Forecasting Economic Activity Using a Neural Network in Uncertain Times: Monte Carlo Evidence and Application to the
German GDP
Oliver Holtemöller, Boris Kozyrev
IWH Discussion Papers,
No. 6,
2024
Abstract
In this study, we analyzed the forecasting and nowcasting performance of a generalized regression neural network (GRNN). We provide evidence from Monte Carlo simulations for the relative forecast performance of GRNN depending on the data-generating process. We show that GRNN outperforms an autoregressive benchmark model in many practically relevant cases. Then, we applied GRNN to forecast quarterly German GDP growth by extending univariate GRNN to multivariate and mixed-frequency settings. We could distinguish between “normal” times and situations where the time-series behavior is very different from “normal” times such as during the COVID-19 recession and recovery. GRNN was superior in terms of root mean forecast errors compared to an autoregressive model and to more sophisticated approaches such as dynamic factor models if applied appropriately.
Read article
Tracking Weekly State-Level Economic Conditions
Christiane Baumeister, Danilo Leiva-León, Eric Sims
Review of Economics and Statistics,
No. 2,
2024
Abstract
This paper develops a novel dataset of weekly economic conditions indices for the 50 U.S. states going back to 1987 based on mixed-frequency dynamic factor models with weekly, monthly, and quarterly variables that cover multiple dimensions of state economies. We find considerable cross-state heterogeneity in the length, depth, and timing of business cycles. We illustrate the usefulness of these state-level indices for quantifying the main contributors to the economic collapse caused by the COVID-19 pandemic and for evaluating the effectiveness of the Paycheck Protection Program. We also propose an aggregate indicator that gauges the overall weakness of the U.S. economy.
Read article
Is Risk the Fuel of the Business Cycle? Financial Frictions and Oil Market Disturbances
Christoph Schult
IWH Discussion Papers,
No. 4,
2024
Abstract
I estimate a dynamic stochastic general equilibrium (DSGE) model for the United States that incorporates oil market shocks and risk shocks working through credit market frictions. The findings of this analysis indicate that risk shocks play a crucial role during the Great Recession and the Dot-Com bubble but not during other economic downturns. Credit market frictions do not amplify persistent oil market shocks. This result holds as long as entry and exit rates of entrepreneurs are independent of the business cycle.
Read article
Research Clusters
Three Research Clusters Research Cluster "Economic Dynamics and Stability" Research Questions This cluster focuses on empirical analyses of macroeconomic dynamics and stability.…
See page
Guiding Theme and Research Profile
Tasks of the IWH Guided by its mission statement , the IWH places the understanding of the determinants of long term growth processes at the centre of the research agenda. Long…
See page
Organisation of Research
Tasks of the IWH Guided by its mission statement , the IWH places the understanding of the determinants of long term growth processes at the centre of the research agenda. Long…
See page
The Importance of Credit Demand for Business Cycle Dynamics
Gregor von Schweinitz
IWH Discussion Papers,
No. 21,
2023
Abstract
This paper contributes to a better understanding of the important role that credit demand plays for credit markets and aggregate macroeconomic developments as both a source and transmitter of economic shocks. I am the first to identify a structural credit demand equation together with credit supply, aggregate supply, demand and monetary policy in a Bayesian structural VAR. The model combines informative priors on structural coefficients and multiple external instruments to achieve identification. In order to improve identification of the credit demand shocks, I construct a new granular instrument from regional mortgage origination.
I find that credit demand is quite elastic with respect to contemporaneous macroeconomic conditions, while credit supply is relatively inelastic. I show that credit supply and demand shocks matter for aggregate fluctuations, albeit at different times: credit demand shocks mostly drove the boom prior to the financial crisis, while credit supply shocks were responsible during and after the crisis itself. In an out-of-sample exercise, I find that the Covid pandemic induced a large expansion of credit demand in 2020Q2, which pushed the US economy towards a sustained recovery and helped to avoid a stagflationary scenario in 2022.
Read article
Understanding Post-Covid Inflation Dynamics
Martín Harding, Jesper Lindé, Mathias Trabandt
Journal of Monetary Economics,
November
2023
Abstract
We propose a macroeconomic model with a nonlinear Phillips curve that has a flat slope when inflationary pressures are subdued and steepens when inflationary pressures are elevated. The nonlinear Phillips curve in our model arises due to a quasi-kinked demand schedule for goods produced by firms. Our model can jointly account for the modest decline in inflation during the Great Recession and the surge in inflation during the post-COVID period. Because our model implies a stronger transmission of shocks when inflation is high, it generates conditional heteroskedasticity in inflation and inflation risk. Hence, our model can generate more sizeable inflation surges due to cost-push and demand shocks than a standard linearized model. Finally, our model implies that the central bank faces a more severe trade-off between inflation and output stabilization when inflation is elevated.
Read article
Jobs at IWH
Vacancies at IWH The Halle Institute for Economic Research (IWH) – Member of the Leibniz Association was founded in 1992. IWH’s tasks are economic research and science-based…
See page
Exploring Accounting Research Topic Evolution: An Unsupervised Machine Learning Approach
June Cao, Zhanzhong Gu, Iftekhar Hasan
Journal of International Accounting Research,
No. 3,
2023
Abstract
This study explores the evolution of accounting research by utilizing an unsupervised machine learning approach. We aim to identify the latent topics of accounting from the 1980s up to 2018, the dynamics and emerging topics of accounting research, and the economic reasons behind those changes. First, based on 23,220 articles from 46 accounting journals, we identify 55 topics using the latent Dirichlet allocation model. To illustrate the connection between topics, we use HistCite to generate a citation map along a timeline. The citation clusters demonstrate the “tribalism” phenomenon in accounting research. We then implement the dynamic topic model to reveal the dynamics of topics to show changes in accounting research. The emerging research trends are identified from the topic analytics. We further explore the economic reasons and in-depth insights into the topic evolution, indicating the economic development embeddedness nature of accounting research.
Read article
