New Economics Papers
on Risk Management
Issue of 2005‒04‒16
twenty papers chosen by

  1. Nonparametric Estimation of Conditional Expected Shortfall By Olivier SCAILLET
  2. Geographic Versus Industry Diversification: Contraints Matter By Paul EHLING; Sofia B. RAMOS
  3. Predicting Tail-related Risk Measures: The Consequences of Using GARCH Filters for non-GARCH Data By Amine JALAL; Michael ROCKINGER
  4. A Kolmogorov-Smirnov Type Test for Positive Quadrant Dependence By Olivier Scaillet
  5. Exchange Rate Volatilities and Time-varying Risk Premium in East Asia By Chae-Shick Chung; Doo Yong Yang
  6. Risk Managing Bermudan Swaptions in the Libor BGM Model By Raoul Pietersz; Antoon Pelsser
  7. A Comparison of Single Factor Markov-functional and Multi Factor Market Models By Raoul Pietersz; Antoon Pelsser
  8. Generic Market Models By Raoul Pietersz; Marcel van Regenmortel
  9. Business cycle effects on Portfolio Credit Risk: scenario generation through Dynamic Factor analysis By rea cipollini; giuseppe missaglia
  10. Measurement of Financial Risk Persistence By Cornelis A. Los
  11. Measuring Loss Potential of Hedge Fund Strategies By Marcos Mailoc López de Prado; Achim Peijan
  12. An Empirical Analysis of Equity Default Swaps (II): Multivariate Insights By Norbert_Jobst; Arnaud_de_Servigny
  13. LIQUIDITY RISK ESTIMATION USING FUZZY MEASURE THEORY By Sebastián Alberto Rey; Javier Ignacio García-Fronti; María Teresa Casparri
  14. Investigating Non-Linearities in the Relationship Between Real Exchange Rate Volatility and Trade By Olivier Bonroy; Jean-Philippe Gervais; Bruno Larue
  15. Monetary Convergence And Risk Premiums In The EU Candidate Countries By Lucjan T Orlowski
  16. Modeling the risk process in the XploRe computing environment By Krzysztof Burnecki; Rafal Weron
  17. History and the Equity Risk Premium By William N. Goetzmann; Roger Ibbotson
  18. Performance Persistence By WILLIAM N. GOETZMANN; STEPHEN J. BROWN
  19. Components of the Czech Koruna Risk Premium in a Multiple-Dealer FX Market By Alexis Derviz
  20. Predicting Bank CAMELS and S&P Ratings: The Case of the Czech Republic By Alexis Derviz; Jiří Podpiera

  1. By: Olivier SCAILLET (HEC-University of Geneva and FAME)
    Abstract: We consider a nonparametric method to estimate conditional expected shortfalls, i.e. conditional expected losses knowing that losses are larger than a given loss quantile. We derive the asymptotic properties of kernal estimators of conditional expected shortfalls in the context of a stationary process satisfying strong mixing conditions. An empirical illustration is given for several stock index returns, namely CAC40, DAX30, S&P500, DJI, and Nikkei225.
    Keywords: Nonparametric; Kernel; Time series; Conditional VAR; Conditional expected shortfall; Risk management; Loss severity distribution
    JEL: C14 D81 G10 G21 G22 G28
    Date: 2004–05
  2. By: Paul EHLING (Penn State University, Smeal College); Sofia B. RAMOS (ISCTE Business School)
    Abstract: This research addresses whether geographic diversification provides benefits over industry diversification in a sample of European country and industry indexes. The methodology allows performance comparisons with short-selling constraints, upper and lower bounds, and many benchmarks. In the absence of constraints, no empirical evidence is found to support the argument that country diversification is a superior approach. In the case of realistic weights on portfolios such as short-selling, and lower or upper bonds, geographic diversification performs (sig-nificantly) better. The contrary results appear to be attributable to the fact that industry portfolios are better suited to eliminate the single dominant factor risk in stock returns. Further out-of-sample analysis shows that geographic diversification performs better, although the tests do not show statistical significance.
    Keywords: Diversification gains; EMU; Geographic diversification; Industry diversification
    JEL: G11 G15
    Date: 2004–08
  3. By: Amine JALAL (HEC-University of Lausanne and FAME); Michael ROCKINGER (HEC-University of Lausanne, FAME and CEPR)
    Abstract: We investigate the consequences for value-at-risk and expected short-fall purposes of using a GARCH filter on various mis-specified processes. We show that careful investigation of the adequacy of the GARCH filter is necessary since under mis-specifications a GARCH filter appears to do more harm than good. Using an unconditional non filtered tail estimate appears to perform satisfactorily for dependent data with a degree of dependency corresponding to actual market conditions.
    Keywords: Extreme value theory; Value at Risk (VaR); Expected shortfall; GARCH; Markov switching; Jump diffusion; Backtesting.
    JEL: G12 C32
    Date: 2004–06
  4. By: Olivier Scaillet (HEC, University of Geneva and FAME)
    Abstract: We consider a consistent test, that is similar to a Kolmogorov-Smirnov test, of the complete set of restrictions that relate to the copula representation of positive quadrant dependence. For such a test we propose and justify inference relying on a simulation based multiplier method and a bootstrap method. We also explore the finite sample behaviour of ^ both methods with Monte Carlo experiments. A first empirical illustration is given for US insurance claim data. A second one exemines the presence of positive quadrant dependence in life expectancies at birth of males and females among countries.
    Keywords: Nonparametric; Positive Quadrant Dependence; Copula; Risk Management; Loss Severity Distribution; Bootstrap; Multiplier Method; Empirical Process
    JEL: C12 D81 G10 G21 G22
  5. By: Chae-Shick Chung (Korea Institute for International Economic Policy); Doo Yong Yang (Korea Institute for International Economic Policy)
    Abstract: This paper is to analyze characteristics of the foreign exchange market in four major East Asian countries (Korea, Thailand, Singapore and Japan) before and after the financial crisis to get implicatoins of it. Our focus is given on the relationship between exchange rate volatilities and risk premium on the selected countries. The crisis-hit countries in the region including Korean and Thailand show structural break during the Asian crisis in representing higher standard deviations on nominal exchange rates since 1997. However, it is argued that they returned to the previous rigid exchange movements due to a fear of floating. Nevertheless, it is believed that the exchange rate arrangements in crisis-hit countries differ from the previous psedo-dollar pegged system.
    Keywords: Exchange rate volatility, risk premium foreign exchange, market in East Asia, financial crisis, foreign exchange rate, Korea, Thailand, Singapore, Japan
    JEL: F31 G12
    Date: 2004–10
  6. By: Raoul Pietersz (Erasmus University Rotterdam); Antoon Pelsser (Erasmus University Rotterdam)
    Abstract: This article presents a novel approach for calculating swap vega per bucket in the Libor BGM model. We show that for some forms of the volatility an approach based on re-calibration may lead to a large uncertainty in estimated swap vega, as the instantaneous volatility structure may be distorted by re-calibration. This does not happen in the case of constant swap rate volatility. We then derive an alternative approach, not based on re-calibration, by comparison with the swap market model. The strength of the method is that it accurately estimates vegas for any volatility function and at a low number of simulation paths. The key to the method is that the perturbation in the Libor volatility is distributed in a clear, stable and well understood fashion, whereas in the re-calibration method the change in volatility is hidden and potentially unstable.
    Keywords: central interest rate model, Libor BGM model, swaption vega, risk management, swap market model, Bermudan swaption
    JEL: G13
    Date: 2005–02–11
  7. By: Raoul Pietersz (Erasmus University Rotterdam); Antoon Pelsser (Erasmus University Rotterdam)
    Abstract: We compare single factor Markov-functional and multi factor market models for hedging performance of Bermudan swaptions. We show that hedging performance of both models is comparable, thereby supporting the claim that Bermudan swaptions can be adequately risk-managed with single factor models. Moreover, we show that the impact of smile can be much larger than the impact of correlation. We propose a new method for calculating risk sensitivities of callable products in market models, which is a modification of the least-squares Monte Carlo method. The hedge results show that this new method enables proper functioning of market models as risk-management tools.
    Keywords: Markov-functional model, market model, Bermudan swaption, terminal correlation, hedging, Greeks for callable products, smile
    JEL: G13
    Date: 2005–02–11
  8. By: Raoul Pietersz (Erasmus University Rotterdam); Marcel van Regenmortel (ABN AMRO Bank)
    Abstract: Currently, there are two market models for valuation and risk management of interest rate derivatives, the LIBOR and swap market models. In this paper, we introduce arbitrage-free constant maturity swap (CMS) market models and generic market models featuring forward rates that span periods other than the classical LIBOR and swap periods. We develop generic expressions for the drift terms occurring in the stochastic differential equation driving the forward rates under a single pricing measure. The generic market model is particularly apt for pricing of Bermudan CMS swaptions, fixed-maturity Bermudan swaptions, and callable hybrid coupon swaps.
    Keywords: market model, generic market models, generic drift terms, hybrid products, BGM model
    JEL: G13
    Date: 2005–02–11
  9. By: rea cipollini (queen mary university of london); giuseppe missaglia (iccrea)
    Abstract: In this paper, we focus on measuring the risk associated to a bank loan portfolio. In particular, we depart from the standard one factor model representation of portfolio credit risk. In particular, we consider an hetrogeneous portfolio, and we account for stochastic dependent recoveries. We also examine the influence of either one systemic shock (interpreted as the state of the business cycle) or two systemic shocks (interpreted as demand and supply innovations) on portfolio credit risk. The identification and estimation of the common shocks is obtained by fitting a Dynamic Factor model to a large number of macro credit drivers. The scenarios are obtained by employing Montecarlo stochastic simulation.
    Keywords: Risk management default correlation Dynamic Factor
    JEL: C32 E17 G20
    Date: 2005–02–11
  10. By: Cornelis A. Los (Kent State University)
    Abstract: This paper discusses various ways of measuring the persistence or Long Memory (LM) of financial market risk in both its time and frequency domains. For the measurement of the risk, irregularity or 'randomness' of these series, we can compute a set of critical Lipschitz - Hölder exponents, in particular, the Hurst Exponent and the Lévy Stability Alpha, and relate them to the Mandelbrot-Hoskings' fractional difference operators, as occur in the Fractional Brownian Motion model (which is our benchmark). The main contribution of this paper is to provide a compaison table of the various critical exponents available in various scientific disciplines to measure the LM persistence of time seies. It also discusses why Markov- and (G)ARCH models cannot capture this LM, long term dependence or risk persistence, because these models have finite lag lengths, while the empirically observed long memory risk phenomenon is an infinite lag length phenomenon. Currently, there are three techniques of nonstationary time series analysis to measure time - varying financial risk: Range/Scale analysis, windowed Fourier analysis, and wavelet MRA. This paper relates these powerful analytic techniques to classical Box-Jenkins-type time series analysis and to Pearson's spectral frequency analysis, which both rely on the uncorroboated assumption of stationarity and ergodicity.
    Keywords: Persistence, long memory, dependence, time series, frequency, critical exponents, fractional Brownian motion, (G)ARCH, risk measurement
    JEL: C15 C23 C53 G10
    Date: 2005–02–13
  11. By: Marcos Mailoc López de Prado (UBS); Achim Peijan (UBS)
    Abstract: We measure the loss potential of Hedge Funds by combining three market risk measures: VaR, Draw-Down and Time Under-The-Water. Calculations are carried out considering three different frameworks regarding Hedge Fund returns: i) Normality and time-independence, ii) Non-normality and time- independence and iii) Non-normality and time-dependence. In the case of Hedge Funds, our results clearly state that market risk may be substantially underestimated by those models which assume Normality or, even considering Non-Normality, neglect to model time- dependence. Moreover, VaR is an incomplete measure of market risk whenever the Normality assumption does not hold. In this case, VaR results must be compared with Draw-Down and Time Under-The-Water measures in order to accurately assess about Hedge Funds loss potential.
    Keywords: Hedge Fund, Value-at-Risk, risk, performance, drawdown, under- the-water, normal returns, non-normal returns, time-dependence, ARMA, Monte Carlo, skewness, kurtosis, mixture of gaussian distributions, survival probability, styles, investment strategies
    JEL: G0 G1 G2 G15 G24 E44
    Date: 2005–03–10
  12. By: Norbert_Jobst (Standard & Poor's); Arnaud_de_Servigny (Standard&Poor's)
    Abstract: Equity default swaps (EDS) - contracts that trigger a payment when the underlying equity price falls below a predetermined level - have attracted much attention recently because of their similarities to credit default swaps (CDS) on the one hand, and American digital puts on the other. Particular interest has been received by Collateral- ized debt obligations (CDOs) referencing a portfolio of EDSs, which not only requires the univariate assessment of the risks inherent in EDSs, but also the analysis of dependencies between EDSs (and other asset classes). In this paper, we specifically address correlation or dependency aspects of EDSs, by applying techniques developed for estimating default correlation. Based on Standard & Poor’s CreditPro and Compustat (North America) databases, extensive empirical research is presented. Amongst the main findings are that EDS correlations for standard strikes/barriers of 30% are significantly higher than default correlations, and increase in barrier level, but only for strikes above 50%. This indicates a barrier dependent correlation concept.
    Keywords: EDS Equity Default Swap Correlation
    JEL: G
    Date: 2005–03–28
  13. By: Sebastián Alberto Rey (UNIVERSIDAD DE BUENOS AIRES); Javier Ignacio García-Fronti (UNIVERSIDAD DE BUENOS AIRES); María Teresa Casparri (UNIVERSIDAD DE BUENOS AIRES)
    Abstract: One of the most relevant issues in the risk analysis of the financial institutions´ investments is to determine the capital allocation in order to maintain its solvency and liquidity in adverse situations. The portfolio risk analysis is necessary for assuring the right selection of that capital to be allocated. Each portfolio has a market risk. This risk is directly related to the losses that can be caused by adverse fluctuations of the portfolio asset prices. In this sense, it is necessary to construct a measure able to quantify the potential losses associated with that exposure. The classical Value-at-Risk measures the pure market risk; therefore, it does not bear some considerations. If a financial institution uses this classical framework to determine the quantity of capital to allocate in order to face its obligations with a certain level of confidence, then the institution does not take into account the partial or total portfolio liquidation consequences at the claim moment. To take into account these consequences is crucial because the number of assets to be sold in the market has an important influence in the price at which the transaction will be made. This influence is determined by the market liquidity at that moment. When these problems take place the financial institution could have liquidity problems to cancel its obligations. This paper develops and applies a Value-at-Risk model regarding prices fluctuations and potential market liquidity problems. Due to uncertainty of market liquidity in the future, the model includes Fuzzy Measure Theory . The first section of the paper presents some fundamental concepts of Fuzzy Measure Theory and Extreme Value Theory . The second section presents a “fuzzified” risk valuation model under the classical assumption of normal distribution for the investment returns; and, taking into consideration the Argentinean financial crisis, also presents the model under an Extreme Value Theory distribution. Both alternatives are applied to a portfolio of Repsol-YPF stocks so as to estimate the risk assumed by the holder.
    Keywords: Liquidity risk, Argentina, fuzzy measure
    JEL: G
    Date: 2005–04–14
  14. By: Olivier Bonroy (CRÉA, Laval University); Jean-Philippe Gervais (CRÉA, Laval University); Bruno Larue (CRÉA, Laval University)
    Abstract: Production and marketing lags in agri-food supply chains force competitive primary producers and food processors to commit to output targets before prices and exchange rates are realized. A theoretical model with one processor and many price-taking primary producers is developed to show that an increase in the volatility of the export price generally increases exports under risk neutrality. Furthermore, relaxing the assumption that the processing firm is risk neutral introduces non- linearities in the relationship between exports and export price volatility. This relationship is empirically investigated using the flexible non-linear inference framework developed by Hamilton (2001). The theoretical model provides the foundation for empirical bilateral export equations for Canadian pork exports to the U.S. and Japan. The empirical investigation supports the hypothesis that export price volatility has statistically significant non-linear effects on Canadian pork exports.
    Keywords: Exchange rate volatility, non-linear flexible inference, production lags, pork exports
    JEL: Q17 C32
    Date: 2005–01–27
  15. By: Lucjan T Orlowski (Sacred Heart University)
    Abstract: This study examines the link between various monetary policy regimes and the ability to manage inflation and exchange rate risk premiums in the EU candidate countries as they undergo monetary convergence to the eurozone. The underlying hypothesis is that a system of 'flexible inflation targeting' may be an optimal policy choice for managing these two categories of risk. A model of inflation and exchange rate risk premiums within the context of inflation targeting is proposed. Recent trends in these risk premiums in Hungary, the Czech Republic and Poland are tested by using the GARCH(1,1) methodology.
    Keywords: inflation risk premium, exchange rate risk premium, inflation targeting, monetary convergence, transition economies
    JEL: E32 E52 P33
    Date: 2005–01–31
  16. By: Krzysztof Burnecki (Hugo Steinhaus Center); Rafal Weron (Hugo Steinhaus Center)
    Abstract: A user friendly approach to modeling the risk process is presented. It utilizes the insurance library of the XploRe computing environment which is accompanied by on-line, hyperlinked and freely downloadable from the web manuals and e-books. The empirical analysis for Danish fire losses for the years 1980-90 is conducted and the best fitting of the risk process to the data is illustrated.
    Keywords: Risk process, Monte Carlo simulation, XploRe computing environment
    JEL: G22
    Date: 2005–02–07
  17. By: William N. Goetzmann (Yale School of Management - International Center for Finance); Roger Ibbotson (Yale School of Management)
    Abstract: We summarize some of our own past findings and place them in the context of the historical development of the idea of the equity risk premium and its empirical measurement by financial economists. In particular, we focus on how the theory of compensation for investment risk developed in the 20th century in tandem with the empirical analysis of historical investment performance. Finally, we update our study of the historical performance of the New York Stock Exchange over the period 1792 to the present, and include a measure of the U.S. equity risk premium over more than two centuries. This last section is based upon indices constructed from individual stock and dividend data collected over a decade of research at the Yale School of Management, and contributions by other scholars.
    Keywords: financial history, equity premium
    JEL: N2 G11
    Date: 2005–04–13
  18. By: WILLIAM N. GOETZMANN (Yale School of Management - International Center for Finance); STEPHEN J. BROWN (NYU Stern School of Business)
    Abstract: We explore performance persistence in mutual funds using absolute and relative benchmarks. Our sample, largely free of survivorship bias, indicates that relative risk-adjusted performance of mutual funds persists, however persistence is mostly due to funds that lag the S&P 500. A profit analysis indicates that poor performance increases the probability of disappearance. A year-by-year decomposition of the persistence effect demonstrates that the relative performance pattern depends upon the time period observed, and it is correlated across managers. Consequently, it is due to a common strategy that is not captured by standard stylistic categories, or risk adjustment procedures.
    JEL: G14
    Date: 2005–04–14
  19. By: Alexis Derviz
    Abstract: The paper proposes a continuous time model of an FX market organized as a multiple dealership. The model reflects a number of salient features of the Czech koruna spot market. The dealers have costly access to the best available quotes. They interpret signals from the joint dealer-customer order flow and decide upon their own quotes and trades in the inter-dealer market. Each dealer uses the observed order flow to improve the subjective estimates of the relevant aggregate variables, which are the sources of uncertainty. One of the risk factors is the size of the cross-border dealer transactions in the FX market. These uncertainties have diffusion form and are dealt with according to the principles of portfolio optimization in continuous time. The model is used to explain the country, or risk, premium in the uncovered national return parity equation for the koruna/euro exchange rate. The two country premium terms that I identify in excess of the usual covariance term (a consequence of the “Jensen inequality effectâ€) are the dealer heterogeneity-induced inter-dealer market order flow component and the dealer Bayesian learning component. As a result, a “dealer-based total return parity†formula links the exchange rate to both the “fundamental†factors represented by the differential of the national asset returns, and the microstructural factors represented by heterogeneous dealer knowledge of the aggregate order flow and the fundamentals. Evidence on the cross-border order flow dependence of the Czech koruna risk premium, in accordance with the model prediction, is documented.
    Keywords: Bayesian learning, FX microstructure, optimizing dealer, uncovered parity.
    JEL: F31 G11 G29 D49 D82
    Date: 2003–06
  20. By: Alexis Derviz; Jiří Podpiera
    Abstract: In this paper we investigate the determinants of the movements in the long-term Standard & Poors and CAMELS bank ratings in the Czech Republic during the period when the three biggest banks, representing approximately 60% of the Czech banking sector’s total assets, were privatized (i.e., the time span 1998–2001). The same list of explanatory variables corresponding to the CAMELS rating inputs employed by the Czech National Bank’s banking sector regulators was examined for both ratings in order to select significant predictors among them. We employed an ordered response logit model to analyze the monthly long-run S&P rating and a panel data framework for the analysis of the quarterly CAMELS rating. The predictors for which we found significant explanatory power are: Capital Adequacy, Credit Spread, the ratio of Total Loans to Total Assets, and the Total Asset Value at Risk. Models based on these predictors exhibited a predictive accuracy of 70%. Additionally, we found that the verified variables satisfactorily predict the S&P rating one month ahead.
    Keywords: Bank rating, CAMELS, ordered logit model, panel data analysis.
    JEL: C53 E58 G21 G33
    Date: 2004–01

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.