Mixture normal Value at Risk models of some European market portfolios

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F12%3A86082694" target="_blank" >RIV/61989100:27510/12:86082694 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Mixture normal Value at Risk models of some European market portfolios
Original language description
The assumption of normal probability distribution belongs to the biggest imperfections of estimating Value at Risk. In point of fact, the returns of financial time series are rather distributed leptokurtic than normally. Moreover, the empirical distributions are often skewed. In these cases, the assumption of normal distribution results in over- or underestimation of VaR especially when the quantiles are very high/low. Therefore it is necessary to put emphasis on respecting the leptokurtic and skewed return distribution. In this paper, we interpret the one out of the method how to estimate VaR with respect to the empirical distributions. We describe the analytical solution of VaR under mixture and Markov-Switching normal distribution condition and we compare the estimates according to both approaches. We also present the estimation method of distribution parameters. Thus, we briefly describe and derive the maximum likelihood method based on the iterative EM-algorithm. Using the four se
Czech name
—
Czech description
—

Project
<a href="/en/project/GPP403%2F12%2FP692" target="_blank" >GPP403/12/P692: Managing and modelling of insurance risks within Solvency II</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Řízení a modelování finančních rizik : sborník příspěvků z 6. mezinárodní vědecké konference : 10.-11. září 2012, Ostrava, Česká republika
ISBN
978-80-248-2835-0
ISSN
—
e-ISSN
—
Number of pages
11
Pages from-to
653-663
Publisher name
VŠB - Technická univerzita Ostrava
Place of publication
Ostrava
Event location
Ostrava
Event date
Sep 10, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000317528600074

Similar results(10)