nep-rmg New Economics Papers
on Risk Management
Issue of 2018‒06‒11
nineteen papers chosen by

  1. Semi-parametric Dynamic Asymmetric Laplace Models for Tail Risk Forecasting, Incorporating Realized Measures By Richard Gerlach; Chao Wang
  2. Understanding Flash Crash Contagion and Systemic Risk: A Micro-Macro Agent-Based Approach By James Paulin; Anisoara Calinescu; Michael Wooldridge
  3. Basel methodological heterogeneity and banking system stability: The case of the Netherlands By Laurence Deborgies Sanches; Marno Verbeek
  4. Is Operational Risk Regulation Forward-looking and Sensitive to Current Risks? By Marco Migueis
  5. Why do risk events occur? Insights from accident models: remarks at the 7th Annual Risk Americas 2018 Conference, New York City By Rosenberg, Joshua V.
  6. Systemic Risk and Financial Fragility in the Chinese Economy: A Dynamic Factor Model Approach By Alexey Vasilenko
  7. Term structure of interest rates: modelling the risk premium using a two horizons framework By Georges Prat; Remzi Uctum
  8. Nonparametric Bayesian volatility estimation By Shota Gugushvili; Frank van der Meulen; Moritz Schauer; Peter Spreij
  9. The Implied Bail-in Probability in the Contingent Convertible Securities Market By Masayuki Kazato; Tetsuya Yamada
  10. Simple Market Timing with Moving Averages By Jukka Ilomaki; Hannu Laurila; Michael McAleer
  11. Dynamic Relation between Volatility Risk Premia of Stock and Oil Returns By NAKAMURA Nobuhiro; OHASHI Kazuhiko
  12. CDS market structure and risk flows: the Dutch case By Anouk Levels; René de Sousa van Stralen; Sînziana Kroon Petrescu; Iman van Lelyveld
  13. Dynamic connectedness of global currencies: a conditional Granger-causality approach By Tan T. M. Le; Franck Martin; Duc K. Nguyenc
  14. "Liquidity Risk And Its Determinants': A Study On Oil And Gas Industry In Tatneft" By Awin, Ejin
  15. Diversification Power of Real Estate Market Securities: The Role of Financial Crisis and Dividend Policy By Metin Ilbasmis; Marc Gronwald; Yuan Zhao
  16. Equity Incentives, Disclosure Quality, and Stock Liquidity Risk By Wruck, Karen H.; Wu, YiLin
  17. Near misses in financial trading: skills for capturing and averting error By Leaver, Meghan; Griffiths, Alex; Reader, Tom W.
  18. Testing for Changes in Forecasting Performance By PERRON, Pierre; YAMAMOTO, Yohei
  19. Municipal Bond Liquidity and Default Risk By Schwert, Michael

  1. By: Richard Gerlach; Chao Wang
    Abstract: The joint Value at Risk (VaR) and expected shortfall (ES) quantile regression model of Taylor (2017) is extended via incorporating a realized measure, to drive the tail risk dynamics, as a potentially more efficient driver than daily returns. Both a maximum likelihood and an adaptive Bayesian Markov Chain Monte Carlo method are employed for estimation, whose properties are assessed and compared via a simulation study; results favour the Bayesian approach, which is subsequently employed in a forecasting study of seven market indices and two individual assets. The proposed models are compared to a range of parametric, non-parametric and semi-parametric models, including GARCH, Realized-GARCH and the joint VaR and ES quantile regression models in Taylor (2017). The comparison is in terms of accuracy of one-day-ahead Value-at-Risk and Expected Shortfall forecasts, over a long forecast sample period that includes the global financial crisis in 2007-2008. The results favor the proposed models incorporating a realized measure, especially when employing the sub-sampled Realized Variance and the sub-sampled Realized Range.
    Date: 2018–05
  2. By: James Paulin; Anisoara Calinescu; Michael Wooldridge
    Abstract: The purpose of this paper is to advance the understanding of the conditions that give rise to flash crash contagion, particularly with respect to overlapping asset portfolio crowding. To this end, we designed, implemented, and assessed a hybrid micro-macro agent-based model, where price impact arises endogenously through the limit order placement activity of algorithmic traders. Our novel hybrid microscopic and macroscopic model allows us to quantify systemic risk not just in terms of system stability, but also in terms of the speed of financial distress propagation over intraday timescales. We find that systemic risk is strongly dependent on the behaviour of algorithmic traders, on leverage management practices, and on network topology. Our results demonstrate that, for high-crowding regimes, contagion speed is a non-monotone function of portfolio diversification. We also find the surprising result that, in certain circumstances, increased portfolio crowding is beneficial to systemic stability. We are not aware of previous studies that have exhibited this phenomenon, and our results establish the importance of considering non-uniform asset allocations in future studies. Finally, we characterise the time window available for regulatory interventions during the propagation of flash crash distress, with results suggesting ex ante precautions may have higher efficacy than ex post reactions.
    Date: 2018–05
  3. By: Laurence Deborgies Sanches; Marno Verbeek
    Abstract: The paper investigates how the mix of credit risk measurement methodologies under Basel capital adequacy rules influenced banking stability in the Netherlands during 2008-2015. It presents a first descriptive analysis that helps to examine the micro-regulation of individual banks and the macro-regulation of the banking system in one unified framework. Its goal is to draw regulators' and researchers' attention to interesting issues based on the comparison of the literature highlighting the weak points of the regulatory framework with what is observed in the dataset. Its purpose is to stimulate discussions on certain methodological and policy options.
    Keywords: macro-regulation; banks; credit rating; Basel methodology
    JEL: G21 G24 G28
    Date: 2018–05
  4. By: Marco Migueis
    Abstract: This article evaluates whether US large bank operational risk capital requirements are forward-looking, sensitive to banks' current exposures, and allow for risk mitigation, and discusses modifications that could bring regulation closer to these goals while also highlighting the potential pitfalls of doing so.
    Date: 2018–05–21
  5. By: Rosenberg, Joshua V. (Federal Reserve Bank of New York)
    Abstract: Remarks at the 7th Annual Risk Americas 2018 Conference, New York City.
    Keywords: organizational accidents; barrier model; information processing model; conflicting objectives model; normal accident model; collective blindness; normalization of deviance; culture of vigilance; risk culture; interactive complexity; tight coupling; risk prevention; root cause analysis
    Date: 2018–05–17
  6. By: Alexey Vasilenko (Bank of Russia, Russian Federation;National Research University Higher School of Economics, Laboratory for Macroeconomic Analysis.)
    Abstract: This paper studies systemic risk and financial fragility in the Chinese economy, applying the dynamic factor model approach. First, we estimate a dynamic factor model to forecast systemic risk that exhibits significant out-of-sample forecasting power, taking into account the effect of several macroeconomic factors on systemic risk, such as economic growth slowdown, large corporate debt, rise of shadow banking, and real estate market slowdown. Second, we analyse the historical dynamics of financial fragility in the Chinese economy over the last ten years using factor-augmented quantile regressions. The results of the analysis demonstrate that the level of fragility in the Chinese financial system decreased after the Global Financial Crisis of 2007-2009, but has been gradually rising since 2015.
    Keywords: systemic risk, financial fragility, factor model, quantile regressions, China .
    JEL: C58 E44 G2
    Date: 2018–03
  7. By: Georges Prat; Remzi Uctum
    Abstract: This paper proposes a hybrid two-horizon risk premium model with one- and two-period maturity debts, among which the risky asset and the riskless one depend on agents’ investment horizon. A representative investor compares at each horizon the ex-ante premium offered by the market with the value they require to take a risky position, with the aim of choosing between a riskless and a risky strategy. Due to market frictions, the premium offered adjusts gradually to its required value determined by the portfolio choice theory. The required market risk premium is defined as a time-varying weighted average of the required 1- and 2-period horizon premia, where the weights represent the degree of preference of the market for each of the horizons. Our framework is more general than the standard model of the term structure of interest rates where it is assumed that the 1-period rate is the riskless rate at any time and for all agents. Setting one period equal to three months, we use 3-month ahead expected values of the US 3-month Treasury Bill rate provided by Consensus Economics surveys to estimate our 3- and 6-month horizon risk premium model using the Kalman filter methodology. We find that both 3- and 6-month maturity rates represent the riskless and the risky rates with a time-varying market preference for the former rate of about two-thirds. This result strongly rejects the standard model and shows the importance of taking into account the market preference for alternative horizons when describing risky strategies in interest rate term structure modelling.
    Keywords: interest rates, risk premium, survey data
    JEL: C51 D84 E43 G11 G14
    Date: 2018
  8. By: Shota Gugushvili; Frank van der Meulen; Moritz Schauer; Peter Spreij
    Abstract: Given discrete time observations over a fixed time interval, we study a nonparametric Bayesian approach to estimation of the volatility coefficient of a stochastic differential equation. We postulate a histogram-type prior on the volatility with piecewise constant realisations on bins forming a partition of the time interval. The values on the bins are assigned an inverse Gamma Markov chain (IGMC) prior. Posterior inference is straightforward to implement via Gibbs sampling, as the full conditional distributions are available explicitly and turn out to be inverse Gamma. We also discuss in detail the hyperparameter selection for our method. Our nonparametric Bayesian approach leads to good practical results in representative simulation examples. Finally, we apply it on a classical data set in change-point analysis: weekly closings of the Dow-Jones industrial averages.
    Date: 2018–01
  9. By: Masayuki Kazato (Deputy Director, Institute for Monetary and Economic Studies, Bank of Japan (E-mail:; Tetsuya Yamada (Director, Institute for Monetary and Economic Studies (currently Financial System and Bank Examination Department), Bank of Japan (E-mail:
    Abstract: The issuance of contingent convertible securities (CoCos) has increased not only in Europe but also in Asia and other areas over the past several years. In this paper, we extend the existing model used to price CoCos to estimate the implied bail-in probability for a variety of CoCos by modifying loss rates for investors due to bail-ins of CoCos. Using our model for empirical analyses, we find that when the credit events occur, the bail-in probability of a CoCo increases by more than the default probability implied by credit default swaps (CDS). The result suggests that the bail-in probability can be used as an early warning indicator of financial crises. We also find that the conditional default probability after bail-in tends to be lower the more CoCos a bank has issued. This finding indicates that investors believe financial institutions become less likely to default as issuing more CoCos strengthens their loss absorption capacity. Overall, our analysis suggests that the market prices of CoCos contain useful information on financial stability.
    Keywords: Market-implied bail-in probability, Contingent convertible securities, Basel III, Financial stability
    JEL: G12 G15 G21 G28 G32 G33
    Date: 2018–05
  10. By: Jukka Ilomaki (University of Tampere, Finland); Hannu Laurila (University of Tampere, Finland); Michael McAleer (Asia University, Taiwan)
    Abstract: Consider using the simple moving average (MA) rule of Gartley (1935) to determine when to buy stocks, and when to sell them and switch to the risk-free rate. In comparison, how might the performance be affected if the frequency is changed to the use of MA calculations? The empirical results show that, on average, the lower is the frequency, the higher are average daily returns, even though the volatility is virtually unchanged when the frequency is lower. The volatility from the highest to the lowest frequency is about 30% lower as compared with the buy-and-hold strategy volatility, but the average returns approach the buy-and-hold returns when frequency is lower. The 30% reduction in volatility appears if we invest randomly half the time in stock markets and half in the risk-free rate.
    Keywords: Market timing; Moving averages; Risk-free rate; Returns and volatility
    JEL: G32 C58 C22 C41 D23
    Date: 2018–05–18
  11. By: NAKAMURA Nobuhiro; OHASHI Kazuhiko
    Abstract: Volatility risk premium (VRP), defined as the difference between implied and realized volatilities, is found to have predictive power on the returns of many different assets (e.g., stocks, exchange rates, and commodities). While most of the extant research analyzes the return predictability of VRP, in this paper, we instead investigate the relation between the VRP of different assets, specifically stocks and oil. Using daily data of VRP from May 10, 2007 to May 16, 2017, we conduct VAR analyses on the stock and oil VRP and find that the effects of the stocks VRP on the oil VRP are limited and short-lived, if any. On the other hand, the VRP of oil has significantly positive and long-lasting effects on that of stocks after the outbreak of financial crises. These results suggest that the investors' sentiments (measured by VRP) are transmitted from the oil market to the stock market over time, but not the other way around, which is rather unexpected because financialization of commodities means a massive increase in investment in commodities by investors in traditional stock and bond markets, and hence the direction of effects is thought to be from the stock market to the commodity market.
    Date: 2018–05
  12. By: Anouk Levels; René de Sousa van Stralen; Sînziana Kroon Petrescu; Iman van Lelyveld
    Abstract: Using new regulatory data, this paper contributes to the growing literature on derivatives markets and (systemic) risk, by providing a first account of the Dutch CDS market, investigating the factors that drive buying and selling of credit protection ('flow-of risk'), and analysing the impact of Brexit. We find that the CDS market has a 'core-periphery' structure in which Dutch banks are CDS sellers while insurance firms and pension funds (ICPF's) and 'other financial institutions' (OFIs) are buyers. When the volatility of a reference entity increases, the propensity to sell CDS decreases for banks and increases for ICPFs and OFIs. This hints at procyclical behaviour by banks and countercyclical behaviour by ICPFs and OFIs. The 'core-periphery' structure of the CDS market became more pronounced around Brexit events, making the CDS market more vulnerable to shocks emanating from 'systemic' players. Banks reduced net buying and selling of CDS protection on UK reference entities, while OFIs and investment funds became more dominant. This underpins the importance of adequate buyers for systemic institutions and extending the regulatory perimeter beyond banking.
    Keywords: EMIR; trade repositories; CDS markets; Brexit
    JEL: G15 G18
    Date: 2018–05
  13. By: Tan T. M. Le (Univ Rennes, CREM, CNRS, UMR 6211, F-35000 Rennes, France, and Hue University, Vietnam); Franck Martin (Univ Rennes, CREM, CNRS, UMR 6211, F-35000 Rennes, France,); Duc K. Nguyenc (Ipag Business School, Paris, France)
    Abstract: Conditional granger causality framework in Barnett and Seth (2014) is employed to measure the connectedness among the most globally traded currencies. The connectedness exhibits dynamics through time on both breadth and depth dimensions at three levels: node-wise, group-wise and system-wise. Overall, rolling connectedness series could capture major systemic events like Lehman Brothers'collapse and the get-through of Outright Monetary Transactions in Europe in September 2012. The rolling total breath connectedness series spike during high-risk episodes, becomes more stable in lower risk environment and is positively correlated with volatility index and Ted spread, thus, can be considered as a systemic risk indicator in light of Billio et al. (2012). Global currencies tend structure into communities based on connection strength and density. While more links are found related to currencies from emerging markets, G11 currencies are net spreaders of foreign exchange rate returns. Finally, hard currencies including Canadian dollar, Norwegian Krone and Japanese Yen frequently present among the top most connected, though the centrality positions vary over time.
    Keywords: conditional granger causality, exchange rates, connectedness, systemic risk
    Date: 2018–04
  14. By: Awin, Ejin
    Abstract: ABSTRACT Liquidity risk management is an important aspect in the organisation. In order to avoid efficiency, it is important for an organisation to manage liquidity risk. Hence, this study attempted to investigate the influence of firm-specific factors and macro-economic factors affecting liquidity risk of oil and gas industry in Tatneft. This study employs time series analysis from 2012 to 2016. The analysis shows that firm-specific factors (average collection period and corporate governance index score) and macro-economic factor (company’s beta) influence the liquidity risk of the industry. This study suggest that the firms should manage their account receivable efficiently by establishing clear credit policy and incorporate more corporate governance elements such as transparency, accountability, fairness, and independence in the firms to make the company more efficient.
    Keywords: Liquidity risk, Average collection period, Corporate governance
    JEL: G3
    Date: 2018–05–15
  15. By: Metin Ilbasmis; Marc Gronwald; Yuan Zhao
    Abstract: This paper investigates dynamic conditional correlations between stock and REIT markets in both Turkey and the U.S. We use an Asymmetric DCC - GJR - GARCH model to estimate the dynamic conditional correlation at daily, weekly, and monthly frequencies. Our contribution is threefold. First, we find a that downward trend in the daily conditional correlation in the Turkish market, which is contrary to the literature, while the upward trend in the correlation of the two U.S. markets is consistent with the literature. Second, we observe that the trend in the correlation changes the direction with the 2008 Global Financial Crisis. The negative trend in Turkish market becomes positive and the positive trend in the U.S. market becomes negative after the crisis, which could indicate a structural break in the REIT market caused by the crisis. Third, we find that the dividend policy of REITs plays an important role on the dynamics of the correlation. Dividend payments by Turkish REITs decrease their conditional correlation with the Turkish stock market while no such relationship is detected in the U.S. We argue that both the relationship between dividend payments by REITs and REIT correlation with the stock index is associated with the different regulatory environment of REITs in Turkey.
    Keywords: REITs, equity, correlations, DCC-GARCH, deterministic trend, dividend policy
    JEL: C51 C58
    Date: 2018
  16. By: Wruck, Karen H. (Ohio State University); Wu, YiLin (National Taiwan University)
    Abstract: We provide evidence that CEO equity incentives, especially stock options, influence stock liquidity risk via information disclosure quality. We document a negative association between CEO options and the quality of future managerial disclosure policy. Contributing to the literature on CEO risk-taking, we document a positive association between CEO options and future systematic stock liquidity risk. Controlling for endogeneity, we show that information disclosure quality is an important channel through which CEO options influence stock liquidity risk. Results are robust to various controls for endogeneity and to the use of numerous disclosure quality and stock liquidity risk measures.
    JEL: D22 G12 G32 G34 J33 J41 O31
    Date: 2017–02
  17. By: Leaver, Meghan; Griffiths, Alex; Reader, Tom W.
    Abstract: Objective: The aims of this study were (a) to determine whether near-miss incidents in financial trading contain information on the operator skills and systems that detect and prevent near misses and the patterns and trends revealed by these data and (b) to explore if particular operator skills and systems are found as important for avoiding particular types of error on the trading floor. Background: In this study, we examine a cohort of near-miss incidents collected from a financial trading organization using the Financial Incident Analysis System and report on the nontechnical skills and systems that are used to detect and prevent error in this domain. Method: One thousand near-miss incidents are analyzed using distribution, mean, chi-square, and associative analysis to describe the data; reliability is provided. Results: Slips/lapses (52%) and human–computer interface problems (21%) often occur alone and are the main contributors to error causation, whereas the prevention of error is largely a result of teamwork (65%) and situation awareness (46%) skills. No matter the cause of error, situation awareness and teamwork skills are used most often to detect and prevent the error. Conclusion: Situation awareness and teamwork skills appear universally important as a “last line” of defense for capturing error, and data from incident-monitoring systems can be analyzed in a fashion more consistent with a “Safety-II” approach. Application: This research provides data for ameliorating risk within financial trading organizations, with implications for future risk management programs and regulation.
    Keywords: accidents; human error; situation awareness; cognition; team collaboration; teams and groups; social processes; safety culture and behavior change
    JEL: F3 G3
    Date: 2018–05–09
  18. By: PERRON, Pierre; YAMAMOTO, Yohei
    Abstract: We consider the issue of forecast failure (or breakdown) and propose methods to assess retrospectively whether a given forecasting model provides forecasts which show evidence of changes with respect to some loss function. We adapt the classical structural change tests to the forecast failure context. First, we recommend that all tests should be carried with a fixed scheme to have best power. This ensures a maximum difference between the fitted in and out-of-sample means of the losses and avoids contamination issues under the rolling and recursive schemes. With a fixed scheme, Giacomini and Rossi's (2009) (GR) test is simply a Wald test for a one-time change in the mean of the total (the in-sample plus out-of-sample) losses at a known break date, say m, the value that separates the in and out-of-sample periods. To alleviate this problem, we consider a variety of tests: maximizing the GR test over all possible values of m within a pre-specified range; a Double sup-Wald (DSW) test which for each m performs a sup-Wald test for a change in the mean of the out-of-sample losses and takes the maximum of such tests over some range; we also propose to work directly with the total loss series to define the Total Loss sup-Wald (TLSW) test and the Total Loss UDmax (TLUD) test. Using extensive simulations, we show that with forecasting models potentially involving lagged dependent variables, the only tests having a monotonic power function for all data-generating processes are the DSW and TLUD tests, constructed with a fixed forecasting window scheme. Some explanations are provided and two empirical applications illustrate the relevance of our findings in practice.
    Keywords: forecast failure, non-monotonic power, structural change, out-of-sample method
    JEL: C14 C22
    Date: 2018–05
  19. By: Schwert, Michael (Ohio State University)
    Abstract: This paper examines the pricing of bonds issued by states and local governments. I use three distinct, complementary approaches to decompose municipal bond spreads into default and liquidity components, finding that default risk accounts for 74% to 84% of the average municipal bond spread after adjusting for tax-exempt status. The first approach estimates the liquidity component using transaction data, the second measures the default component with credit default swap data, and the third is a quasi-natural experiment that estimates changes in default risk around pre-refunding events. The price of default risk is high given the rare incidence of municipal default and implies a high risk premium.
    JEL: G12 H74
    Date: 2016–09

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.