Developing a stress testing framework based on market risk models

Bank Vulnerability and Financial Soundness Testing: the Bank Resilience Index

“…They found evidence that the US banking system has improved since the recent financial crisis and outlined the value of stress testing as a macro-prudential policy tool. on the other hand, Alexander & Sheedy (2008) developed a bottom-up procedure, based on market risk models, to directly stress portfolios held by banks that can incorporate both volatility clustering and heavy tails. They explored eight risk models based on VAR and Conditional VAR (CVAR): they found strong evidence that the best risk model, for stress testing purposes, is the conditional empirical model developed by Barone-Adesi, Bourgoin & Giannopoulos (1998).…”

“…Stress testing was already a hot topic before crises, anyway, at the beginning of 2000s, when the FSAP (Financial Sector Assessment Program), managed by the IMF, had just been launched, for it was already clear enough that financial stability assessment had to be considered crucial (Blaschke, Jones, majnoni & Peria, 2001). Being the main 53 result of a worsening scenario, a right-hand shifting of the loss probability distribution, the subject was often dealt with, from the very beginning of the debate, in association with the literature about market risk modeling and Value at Risk (Cherubini & della lunga, 1999;Aragones, blanco & dowd, 2001;Teker & Akçay, 2004;Alexander & sheedy, 2008), by also emphasizing the drawbacks of the VAR approach (Lopez, 2005). The very simple, general idea is that a financial intermediary ought to demonstrate to be able to stand up under some adverse economic scenarios.…”

Forecasting portfolio-Value-at-Risk with nonparametric lower tail dependence estimates

“…• Smooth the simulated log returns by kernel density estimation (Epanechnikov kernel) (Pritsker, 2006;Alexander and Sheedy, 2008).…”

Stress Testing in Risk Management: An Application in theTurkish Banking Sector

“…Stress testing is designed to explore the tails of the distribution of losses beyond the threshold (typically 99%) used in Value-at-Risk (VaR) analysis [9]. The advantage of the VAR is that it estimates how write-offs change in the quarters following adverse business cycle shocks implying that the stress test is conditional on the historical correlation among the variables in the multivariate model [10].…”

“…The possibility that bank VaR models are misspecified creates further incentive to ensure that an appropriate model is selected for stress testing purposes. [9] VaR (Value at Risk) is a method based on the probability of deviation from anticipated profit. Given the banks' open positions, it calculates the potential losses arising to banks from price volatility.…”