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
18.12.2018 • 22/2018
IWH leads large scale EU research project on productivity
Is productivity growth slowing in industrialised countries? And if so, why? From the start of 2019, the Halle Institute for Economic Research (IWH) will be addressing these questions as the coordinator of a new EU project. Economists and statistics experts from nine European partners will collaborate on the three-year project, entitled MICROPROD. With a total budget of just under three million euros, it is the IWH’s largest EU project to date.
Steffen Müller
Read press release
13.12.2018 • 21/2018
Economic activity in the world and in Germany is losing momentum
In the second half of 2018, the upturn of the German economy has stalled. Production of the automotive industry declined because of delays in switching production to WLTP compliant cars. Irrespectively of this, the German export business has been weakening since the beginning of the year, since the global economy, burdened by the political uncertainties surrounding trade conflicts, the impending Brexit and the conflict over the Italian budget, was unable to keep up with the high momentum of 2017. “It is to be expected that the less benign external environment will not only dampen exports, but will also impact on companies’ investment and hiring decisions”, says Oliver Holtemöller, head of the Department Macroeconomics and vice president at Halle Institute for Economic Research (IWH). Gross domestic product is expected to increase by 1.5% in 2018 and by 1.4% in 2019, which is roughly equal to the growth rate of economic capacity in Germany.
Oliver Holtemöller
Read press release
Central Bank Transparency and the Volatility of Exchange Rates
Stefan Eichler, Helge Littke
Journal of International Money and Finance,
2018
Abstract
We analyze the effect of monetary policy transparency on bilateral exchange rate volatility. We test the theoretical predictions of a stylized model using panel data for 62 currencies from 1998 to 2010. We find strong evidence that an increase in the availability of information about monetary policy objectives decreases exchange rate volatility. Using interaction models, we find that this effect is more pronounced for countries with a lower flexibility of goods prices, a lower level of central bank conservatism, and a higher interest rate sensitivity of money demand.
Read article
Housing Consumption and Macroprudential Policies in Europe: An Ex Ante Evaluation
Antonios Mavropoulos, Qizhou Xiong
IWH Discussion Papers,
No. 17,
2018
Abstract
In this paper, we use the panel of the first two waves of the Household Finance and Consumption Survey by the European Central Bank to study housing demand of European households and evaluate potential housing market regulations in the post-crisis era. We provide a comprehensive account of the housing decisions of European households between 2010 and 2014, and structurally estimate the housing preference of a simple life-cycle housing choice model. We then evaluate the effect of a tighter LTV/LTI regulation via counter-factual simulations. We find that those regulations limit homeownership and wealth accumulation, reduces housing consumption but may be welfare improving for the young households.
Read article
Expectation Formation, Financial Frictions, and Forecasting Performance of Dynamic Stochastic General Equilibrium Models
Oliver Holtemöller, Christoph Schult
Abstract
In this paper, we document the forecasting performance of estimated basic dynamic stochastic general equilibrium (DSGE) models and compare this to extended versions which consider alternative expectation formation assumptions and financial frictions. We also show how standard model features, such as price and wage rigidities, contribute to forecasting performance. It turns out that neither alternative expectation formation behaviour nor financial frictions can systematically increase the forecasting performance of basic DSGE models. Financial frictions improve forecasts only during periods of financial crises. However, traditional price and wage rigidities systematically help to increase the forecasting performance.
Read article
What Type of Finance Matters for Growth? Bayesian Model Averaging Evidence
Iftekhar Hasan, Roman Horvath, Jan Mares
World Bank Economic Review,
No. 2,
2018
Abstract
We examine the effect of finance on long-term economic growth using Bayesian model averaging to address model uncertainty in cross-country growth regressions. The literature largely focuses on financial indicators that assess the financial depth of banks and stock markets. We examine these indicators jointly with newly developed indicators that assess the stability and efficiency of financial markets. Once we subject the finance-growth regressions to model uncertainty, our results suggest that commonly used indicators of financial development are not robustly related to long-term growth. However, the findings from our global sample indicate that one newly developed indicator—the efficiency of financial intermediaries—is robustly related to long-term growth.
Read article
Do Employers Have More Monopsony Power in Slack Labor Markets?
Boris Hirsch, Elke J. Jahn, Claus Schnabel
ILR Review,
No. 3,
2018
Abstract
This article confronts monopsony theory’s predictions regarding workers’ wages with observed wage patterns over the business cycle. Using German administrative data for the years 1985 to 2010 and an estimation framework based on duration models, the authors construct a time series of the labor supply elasticity to the firm and estimate its relationship to the unemployment rate. They find that firms possess more monopsony power during economic downturns. Half of this cyclicality stems from workers’ job separations being less wage driven when unemployment rises, and the other half mirrors that firms find it relatively easier to poach workers. Results show that the cyclicality is more pronounced in tight labor markets with low unemployment, and that the findings are robust to controlling for time-invariant unobserved worker or plant heterogeneity. The authors further document that cyclical changes in workers’ entry wages are of similar magnitude as those predicted under pure monopsonistic wage setting.
Read article
19.04.2018 • 7/2018
Joint Economic Forecast Spring 2018: Germany’s Economic Experts Raise Forecast Slightly
Berlin, 19 April – Germany’s leading economic experts raised their forecasts for 2018 and 2019 slightly in their Spring Joint Economic Forecast released on Thursday in Berlin. They now expect economic growth of 2.2 percent for this year and 2.0 percent for 2019, versus 2.0 percent and 1.8 percent respectively in their autumn forecast. “The German economy is still booming, but the air is getting thinner as unused capacities are shrinking“, notes Timo Wollmershaeuser, ifo Head of Economic Forecasting. Commenting on the new German government’s economic policy, he adds: “It is precisely when the government’s coffers are full that fiscal policy should reflect the implications of its actions for overall economic stability and the sustainability of public finances. The extension of statutory pension benefits outlined in the coalition agreement runs counter to the idea of sustainability.”
Oliver Holtemöller
Read press release