Projects
Our Projects 07.2022 ‐ 12.2026 Evaluation of the InvKG and the federal STARK programme On behalf of the Federal Ministry of Economics and Climate Protection, the IWH and the RWI…
See page
The Appropriateness of the Macroeconomic Imbalance Procedure for Central and Eastern European Countries
Geraldine Dany-Knedlik, Martina Kämpfe, Tobias Knedlik
Empirica,
No. 1,
2021
Abstract
The European Commission’s Scoreboard of Macroeconomic Imbalances is a rare case of a publicly released early warning system. It was published first time in 2012 by the European Commission as a reaction to public debt crises in Europe. So far, the Macroeconomic Imbalance Procedure takes a one-size-fits-all approach with regard to the identification of thresholds. The experience of Central and Eastern European Countries during the global financial crisis and in the resulting public debt crises has been largely different from that of other European countries. This paper looks at the appropriateness of scoreboard of the Macroeconomic Imbalances Procedure of the European Commission for this group of catching-up countries. It is shown that while some of the indicators of the scoreboard are helpful to predict crises in the region, thresholds are in most cases set too narrow since it largely disregarded the specifics of catching-up economies, in particular higher and more volatile growth rates of various macroeconomic variables.
Read article
Optimizing Policymakers’ Loss Functions in Crisis Prediction: Before, Within or After?
Peter Sarlin, Gregor von Schweinitz
Macroeconomic Dynamics,
No. 1,
2021
Abstract
Recurring financial instabilities have led policymakers to rely on early-warning models to signal financial vulnerabilities. These models rely on ex-post optimization of signaling thresholds on crisis probabilities accounting for preferences between forecast errors, but come with the crucial drawback of unstable thresholds in recursive estimations. We propose two alternatives for threshold setting with similar or better out-of-sample performance: (i) including preferences in the estimation itself and (ii) setting thresholds ex-ante according to preferences only. Given probabilistic model output, it is intuitive that a decision rule is independent of the data or model specification, as thresholds on probabilities represent a willingness to issue a false alarm vis-à-vis missing a crisis. We provide real-world and simulation evidence that this simplification results in stable thresholds, while keeping or improving on out-of-sample performance. Our solution is not restricted to binary-choice models, but directly transferable to the signaling approach and all probabilistic early-warning models.
Read article
Does Machine Learning Help us Predict Banking Crises?
Johannes Beutel, Sophia List, Gregor von Schweinitz
Journal of Financial Stability,
December
2019
Abstract
This paper compares the out-of-sample predictive performance of different early warning models for systemic banking crises using a sample of advanced economies covering the past 45 years. We compare a benchmark logit approach to several machine learning approaches recently proposed in the literature. We find that while machine learning methods often attain a very high in-sample fit, they are outperformed by the logit approach in recursive out-of-sample evaluations. This result is robust to the choice of performance metric, crisis definition, preference parameter, and sample length, as well as to using different sets of variables and data transformations. Thus, our paper suggests that further enhancements to machine learning early warning models are needed before they are able to offer a substantial value-added for predicting systemic banking crises. Conventional logit models appear to use the available information already fairly efficiently, and would for instance have been able to predict the 2007/2008 financial crisis out-of-sample for many countries. In line with economic intuition, these models identify credit expansions, asset price booms and external imbalances as key predictors of systemic banking crises.
Read article
An Evaluation of Early Warning Models for Systemic Banking Crises: Does Machine Learning Improve Predictions?
Johannes Beutel, Sophia List, Gregor von Schweinitz
Abstract
This paper compares the out-of-sample predictive performance of different early warning models for systemic banking crises using a sample of advanced economies covering the past 45 years. We compare a benchmark logit approach to several machine learning approaches recently proposed in the literature. We find that while machine learning methods often attain a very high in-sample fit, they are outperformed by the logit approach in recursive out-of-sample evaluations. This result is robust to the choice of performance measure, crisis definition, preference parameter, and sample length, as well as to using different sets of variables and data transformations. Thus, our paper suggests that further enhancements to machine learning early warning models are needed before they are able to offer a substantial value-added for predicting systemic banking crises. Conventional logit models appear to use the available information already fairly effciently, and would for instance have been able to predict the 2007/2008 financial crisis out-of-sample for many countries. In line with economic intuition, these models identify credit expansions, asset price booms and external imbalances as key predictors of systemic banking crises.
Read article
Optimizing Policymakers' Loss Functions in Crisis Prediction: Before, Within or After?
Peter Sarlin, Gregor von Schweinitz
Abstract
Early-warning models most commonly optimize signaling thresholds on crisis probabilities. The expost threshold optimization is based upon a loss function accounting for preferences between forecast errors, but comes with two crucial drawbacks: unstable thresholds in recursive estimations and an in-sample overfit at the expense of out-of-sample performance. We propose two alternatives for threshold setting: (i) including preferences in the estimation itself and (ii) setting thresholds ex-ante according to preferences only. Given probabilistic model output, it is intuitive that a decision rule is independent of the data or model specification, as thresholds on probabilities represent a willingness to issue a false alarm vis-à-vis missing a crisis. We provide simulated and real-world evidence that this simplification results in stable thresholds and improves out-of-sample performance. Our solution is not restricted to binary-choice models, but directly transferable to the signaling approach and all probabilistic early-warning models.
Read article
Optimizing Policymakers' Loss Functions in Crisis Prediction: Before, Within or After?
Peter Sarlin, Gregor von Schweinitz
Abstract
Early-warning models most commonly optimize signaling thresholds on crisis probabilities. The ex-post threshold optimization is based upon a loss function accounting for preferences between forecast errors, but comes with two crucial drawbacks: unstable thresholds in recursive estimations and an in-sample overfit at the expense of out-of-sample performance. We propose two alternatives for threshold setting: (i) including preferences in the estimation itself and (ii) setting thresholds ex-ante according to preferences only. We provide simulated and real-world evidence that this simplification results in stable thresholds and improves out-of-sample performance. Our solution is not restricted to binary-choice models, but directly transferable to the signaling approach and all probabilistic early-warning models.
Read article
Do We Need New Modelling Approaches in Macroeconomics?
Claudia M. Buch, Oliver Holtemöller
Financial Cycles and the Real Economy: Lessons for CESEE Countries,
2014
Abstract
The economic and financial crisis that emerged in 2008 also initiated an intense discussion on macroeconomic research and the role of economists in society. The debate focuses on three main issues. Firstly, it is argued that economists failed to predict the crisis and to design early warning systems. Secondly, it is claimed that economists use models of the macroeconomy which fail to integrate financial markets and which are inadequate to model large economic crises. Thirdly, the issue has been raised that economists invoke unrealistic assumptions concerning human behaviour by assuming that all agents are self-centred, rationally optimizing individuals. In this paper, we focus on the first two issues. Overall, our thrust is that the above statements are a caricature of modern economic theory and empirics. A rich field of research developed already before the crisis and picked up shortcomings of previous models.
Read article
Do We Need New Modelling Approaches in Macroeconomics?
Claudia M. Buch, Oliver Holtemöller
IWH Discussion Papers,
No. 8,
2014
Abstract
The economic and financial crisis that emerged in 2008 also initiated an intense discussion on macroeconomic research and the role of economists in society. The debate focuses on three main issues. Firstly, it is argued that economists failed to predict the crisis and to design early warning systems. Secondly, it is claimed that economists use models of the macroeconomy which fail to integrate financial markets and which are inadequate to model large economic crises. Thirdly, the issue has been raised that economists invoke unrealistic assumptions concerning human behaviour by assuming that all agents are self-centred, rationally optimizing individuals. In this paper, we focus on the first two issues. Overall, our thrust is that the above statements are a caricature of modern economic theory and empirics. A rich field of research developed already before the crisis and picked up shortcomings of previous models.
Read article
Modelling Macroeconomic Risk: The Genesis of the European Debt Crisis
Gregor von Schweinitz
Hochschulschrift, Juristische und Wirtschaftswissenschaftliche Fakultät der Martin-Luther-Universität Halle-Wittenberg,
2013
Abstract
Diverging European sovereign bond yields after 2008 are the most visible sign of the European debt crisis. This dissertation examines in a first step, to which extent the development of yields is driven by credit and liquidity risk, and how it is influenced by general uncertainty on financial markets. It can be shown that yields are driven to a significant degree by a flight towards bonds of high liquidity in times of high market uncertainty. In a second step, high yields are interpreted as a sign of an existing crisis in the respective country. Using the signals approach, the early-warning capabilities of four different proposals for the design of the scoreboard as part of the “Macroeconomic Imbalances Procedure” (introduced in December 2011 by the European Commission) are tested, advocating a scoreboard including a variety of many different indicators. In a third step, the methodology of the signals approach is extended to include also results on significance.
Read article
