Structured Monte Carlo. Estimated value at risk in a stock portfolio in Colombia

AD-minister

Cecilia Maya Ochoa¹  María Auxiliadora Vergara Cogollo¹ 

[1] Universidad EAFIT

关键词: VaR;    Market Risk;    Full Montecarlo;    Garch;    Egarch;    Parch;    Aparch.;   

DOI  :  

学科分类：社会科学、人文和艺术（综合）

来源: Universidad E A F I T

【 摘 要 】

This research explores various methods to estimate Value at Risk for aportfolio of high and medium liquidity Colombian stocks. It concludesthat, according to the characteristics of these assets, Full Montecarlois more robust than other parametric methods –particularly the Normalmethod-, and the historical simulation. However, to avoid model risk, itrequires a correct specification of the stochastic process followed byeach of the risk factors. Given the evidence of fat tails on the returnseries, volatility models such as GARCH, EGARCH, PARCH and APARCH areused for this purpose. After that, we compare the one-step ahead VaRforecast given by these models with the one obtained by parametricmethods. It is found that Garch models predict VaR better since theycapture the fat tails characteristic of these series. Once thestochastic process for each asset is properly identified, the FullMontecarlo is applied to estimate VaR.

【 授权许可】

Unknown