Institutional Repository of Vilnius University
Vertės pokyčio rizikos vertinimas taikant režimų pasikeitimo bei priklausomybės struktūros vertinimo modelius /
Abstract
dc:descriptionIn the bachelor’s thesis, a 1day and 10day ValueatRisk (VaR) analysis is conducted for two portfolios: index (S&P 500, FTSE 100, and EUROSTOXX 50) and stocks (Disney, Intel, J.P. Morgan). The analysis includes classical benchmark models – Exponential Weighted Moving Average, Historical Simulation, and univariate MSGJRGARCH; the core methodology – MS–GJR–GARCH copula models; as well as alternative models – BEKK and MS–C–MGARCH. The results demonstrate that implemented MS–GJR–GARCH copula models significantly improve VaR estimation accuracy compared to both benchmark and alternative methods. For the index portfolio, when applying 3846 days rolling window over the test period from 2023–02–17 to 2025–03–16, the singleregime volatility model with a Gumbel copula showed the most robust performance. For the stock portfolio, when applying 4019 days window, the singleregime model with a Student–t copula performed best. When setting the rolling window to 500 days and testing over the period from 2009–04–23 to 2025–03–16, all three copulas (Student–t, Normal, and Clayton) paired with singleregime GJRGARCH showed approximately equal accuracy for both portfolios. The main limitation of these models is their poor 10day VaR forecasting performance during highly volatile periods (e.g., COVID–19).
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ivanauskas, Eugenijus Gabrielius,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD239029089&prefLang=en_US