nep-rmg New Economics Papers
on Risk Management
Issue of 2008‒09‒29
eight papers chosen by
Stan Miles
Thompson Rivers University

  1. The Panic of 2007 By Gary B. Gorton
  2. Testing downside risk efficiency under market distress By Jesus Gonzalo; Jose Olmo
  3. Macroeconomic Determinants of the Term Structure of Corporate Spreads By Jun Yang
  4. Estimating hedge fund leverage By Patrick M McGuire; Camilo Kostas Tsatsaronis
  5. Using The Artificial Neural Network (ANN) to Assess Bank Credit Risk: A Case Study of Indonesia By Maximilian J. B. Hall; Dadang Muljawan; Suprayogi; Lolita Moorena
  6. Nouveaux instruments d’évaluation pour le risque financier d’entreprise By Greta Falavigna
  7. EGARCH and Stochastic Volatility: Modeling Jumps and Heavy-tails for Stock Returns By Jouchi Nakajima
  8. Expected Stock Returns and Variance Risk Premia By Tim Bollerslev; Tzuo Hao; George Tauchen

  1. By: Gary B. Gorton
    Abstract: How did problems with subprime mortgages result in a systemic crisis, a panic? The ongoing Panic of 2007 is due to a loss of information about the location and size of risks of loss due to default on a number of interlinked securities, special purpose vehicles, and derivatives, all related to subprime mortgages. Subprime mortgages are a financial innovation designed to provide home ownership opportunities to riskier borrowers. Addressing their risk required a particular design feature, linked to house price appreciation. Subprime mortgages were then financed via securitization, which in turn has a unique design reflecting the subprime mortgage design. Subprime securitization tranches were often sold to CDOs, which were, in turn, often purchased by market value off-balance sheet vehicles. Additional subprime risk was created (though not on net) with derivatives. When the housing price bubble burst, this chain of securities, derivatives, and off-balance sheet vehicles could not be penetrated by most investors to determine the location and size of the risks. The introduction of the ABX indices, synthetics related to portfolios of subprime bonds, in 2006 created common knowledge about the effects of these risks by providing centralized prices and a mechanism for shorting. I describe the relevant securities, derivatives, and vehicles and provide some very simple, stylized, examples to show: (1) how asymmetric information between the sell-side and the buy-side was created via complexity; (2) how the chain of interlinked securities was sensitive to house prices; (3) how the risk was spread in an opaque way; and (4) how the ABX indices allowed information to be aggregated and revealed. I argue that these details are at the heart of the answer to the question of the origin of the Panic of 2007.
    JEL: E1 E32 G2
    Date: 2008–09
  2. By: Jesus Gonzalo; Jose Olmo
    Abstract: In moments of distress downside risk measures like Lower Partial Moments (LPM) are more appropriate than the standard variance to characterize risk. The goal of this paper is to study how to compare portfolios in these situations. In order to do that we show the close connection between mean-risk efficiency sets and stochastic dominance under distress episodes of the market, and use the latter property to propose a hypothesis test to discriminate between portfolios across risk aversion levels. Our novel family of test statistics for testing stochastic dominance under distress makes allowance for testing orders of dominance higher than zero, for general forms of dependence between portfolios and can be extended to residuals of regression models. These results are illustrated in the empirical application for data from US stocks. We show that mean-variance strategies are stochastically dominated by mean-risk efficient sets in episodes of financial distress.
    Keywords: Comovements, Downside risk, Lower partial moments, Market Distress, Mean-risk models, Mean-variance models, Stochastic dominance
    JEL: C1 C2 G1
    Date: 2008–09
  3. By: Jun Yang
    Abstract: We investigate the macroeconomic determinants of corporate spreads using a no-arbitrage technique. Structural shocks are identified by a New-Keynesian model. Treasury bonds are priced in an affine model with time-varying risk premia. Corporate bonds are priced in a reduced-form credit risk model where default risk depends on macroeconomic state variables. Using U.S. data, we find that the monetary policy shock contributes to more than 50% the corporate spread variations at different forecasting horizons. Its contribution, in general, declines with credit classes. In contrast, the aggregate supply and demand shocks contribute more to the spread variations in low credit classes than in high credit classes. In addition, they in general contribute more for longer forecasting horizons.
    Keywords: Debt management; Financial markets; Interest rates
    JEL: E43 E44 G12
    Date: 2008
  4. By: Patrick M McGuire; Camilo Kostas Tsatsaronis
    Abstract: Hedge funds are major players in the international financial system and nimble investment strategies including the use of leverage allow them to build up large positions. Yet the monitoring of systemic risks posed by the build-up of leverage is hampered by incomplete information on hedge funds' balance sheet positions. This paper describes how an extension of "regression-based style analysis" and publicly available data on fund returns yield an indicator of the average amount of funding leverage used by hedge funds. The approach can take into account non-linear exposures through the use of synthetic option returns as possible risk factors. The resulting estimates of leverage are generally plausible for several hedge fund families, in particular those whose returns are well captured by the risk factors used in the estimation. In the absence of more detailed information on hedge fund investments, these estimates can serve as a tool for macro-prudential surveillance of financial system stability.
    Keywords: hedge funds, systemic risk, leverage, style analysis
    Date: 2008–09
  5. By: Maximilian J. B. Hall (Dept of Economics, Loughborough University); Dadang Muljawan (Central Bank of Indonesia); Suprayogi (Industrial Engineering Program, Bandung Institute of Technology, Indonesia); Lolita Moorena (Central Bank of Indonesia Internship program, Bandung Institute of Technology, Indonesia)
    Abstract: Ever since the Asian Financial Crisis, concerns have risen over whether policy-makers have sufficient tools to maintain financial stability. The ability to predict financial disturbances enables the authorities to take precautionary action to minimize their impact. In this context, the authorities may use any financial indicators which may accurately predict shifts in the quality of bank exposures. This paper uses key macro-economic variables (i.e. GDP growth, the inflation rate, stock prices, the exchange rates, and money in circulation) to predict the default rate of the Indonesian Islamic banks’ exposures. The default rates are forecasted using the Artificial Neural Network (ANN) methodology, which incorporates the Bayesian Regularization technique. From the sensitivity analysis, it is shown that stock prices could be used as a leading indicator of future problem.
    Keywords: default risk, artificial neural network, Bayesian regularization, transition matrix.
    JEL: E25 G32 C63 E27 C11
    Date: 2008–07
  6. By: Greta Falavigna (Ceris - Institute for Economic Research on Firms and Growth, Moncalieri (Turin), Italy)
    Abstract: On a wake of Basel II in 2004, banks and financial institutions had focused on the default analysis of firms. In this contribution, artificial neural networks are used for extracting balance-sheet variables determining the default of enterprises on a base of prospective vision. A manufacturing sample and a services one are introduced in the network and then analysed. In this way, the goal has been to show that artificial neural networks were good tools for classifying firms on a base of balance-sheet data. Moreover, these models are also able to underline indices determining the default risk of firm.
    Keywords: Artificial neural networks (ANN), Determinant variables, Default risk, Manufacturing industry, Service industry.
    JEL: C63 G33 L60 L63
    Date: 2008–06
  7. By: Jouchi Nakajima (Institute for Monetary and Economic Studies, Bank of Japan (E-mail:
    Abstract: This paper proposes the EGARCH model with jumps and heavy- tailed errors, and studies the empirical performance of different models including the stochastic volatility models with leverage, jumps and heavy-tailed errors for daily stock returns. In the framework of a Bayesian inference, the Markov chain Monte Carlo estimation methods for these models are illustrated with a simulation study. The model comparison based on the marginal likelihood estimation is provided with data on the U.S. stock index.
    Keywords: Bayesian analysis, EGARCH, Heavy-tailed error, Jumps, Marginal likelihood, Markov chain Monte Carlo, Stochastic volatility
    JEL: C11 C15 G12
    Date: 2008–09
  8. By: Tim Bollerslev; Tzuo Hao; George Tauchen (School of Economics and Management, University of Aarhus, Denmark)
    Abstract: Motivated by the implications from a stylized self-contained general equilibrium model incorporating the effects of time-varying economic uncertainty, we show that the difference between implied and realized variation, or the variance risk premium, is able to explain a non-trivial fraction of the time series variation in post 1990 aggregate stock market returns, with high (low) premia predicting high (low) future returns. Our empirical results depend crucially on the use of “model-free,” as opposed to Black- Scholes, options implied volatilities, along with accurate realized variation measures constructed from high-frequency intraday, as opposed to daily, data. The magnitude of the predictability is particularly strong at the intermediate quarterly return horizon, where it dominates that afforded by other popular predictor variables, like the P/E ratio, the default spread, and the consumption-wealth ratio (CAY).
    Keywords: Equilibrium asset pricing, stochastic volatility, risk neutral expectation, return predictability, option implied volatility, realized volatility, variance risk premium
    JEL: C22 C51 C52 G12 G13 G14
    Date: 2008–09–03

This nep-rmg issue is ©2008 by Stan Miles. 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.