Non-Extensive Value-at-Risk Estimation During Times of Crisis
Value-at-risk is one of the important subjects that extensively used by researchers and practitioners for measuring and managing uncertainty in financial markets. Although value-at-risk is a common risk control instrument, but there are criticisms about its performance. One of these cases, which has been studied in this research, is the value-at-risk underestimation during times of crisis. In these periods, the non-Gaussian behavior of markets intensifies and the estimated value-at-risks by normal models are lower than the real values. In fact, during times of crisis, the probability density of extreme values in financial return series increases and this heavy-tailed behavior of return series reduces the accuracy of the normal value-at-risk estimation models. A potential approach that can be used to describe non-Gaussian behavior of return series, is Tsallis entropy framework and non-extensive statistical methods. In this paper, we have used non-extensive value at risk model for analyzing the behavior of financial markets during times of crisis. By applying q-Gaussian probability density function, we can see a better value-at-risk estimation in comparison with the normal models, especially during times of crisis. We showed that q-Gaussian model estimates value-at-risk better than normal model. Also we saw in the mature markets, it is obvious that the difference of value-at-risk between normal condition and non-extensive approach increase more than one standard deviation during times of crisis, but in the emerging markets we cannot see a specific pattern.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DeepASL: Kinetic Model Incorporated Loss for Denoising Arterial Spin Labeled MRI via Deep Residual Learning
Arterial spin labeling (ASL) allows to quantify the cerebral blood flow (CBF) by magnetic labeling of the arterial blood water. ASL is increasingly used in clinical studies due to its noninvasiveness, repeatability and b…
Denoisingparameter estimationControlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration
Constrained Reinforcement Learning (CRL) aims to maximize cumulative rewards while satisfying constraints. However, existing CRL algorithms often encounter significant constraint violations during training, limiting thei…
Reinforcement LearningEmpirical Risk Minimization for Losses without Variance
This paper considers an empirical risk minimization problem under heavy-tailed settings, where data does not have finite variance, but only has $p$-th moment with $p \in (1,2)$. Instead of using estimation procedure base…
A cost of capital approach to determining the LGD discount rate
Loss Given Default (LGD) is a key risk parameter in determining a bank's regulatory capital. During LGD-estimation, realised recovery cash flows are to be discounted at an appropriate rate. Regulatory guidance mandates t…
Predicting Value at Risk for Cryptocurrencies With Generalized Random Forests
We study the prediction of Value at Risk (VaR) for cryptocurrencies. In contrast to classic assets, returns of cryptocurrencies are often highly volatile and characterized by large fluctuations around single events. Anal…
quantile regression