• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.92.2007.tde-07062023-142638
Document
Author
Full name
Antonio Marcos de Oliveira Costa
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2007
Supervisor
Committee
Dreifus, Henrique Von (President)
Fonseca Junior, Amaury
Forger, Frank Michael
Title in Portuguese
Cálculo do valor em risco de carteiras com grandes posições: uma abordagem baseada na teoria dos valores extremos
Keywords in Portuguese
Administração de risco
Finanças
Mercado de capitais
Abstract in Portuguese
Em geral, o Valor em Risco - ou simplesmente VaR - de uma carteira é estimado para um horizonte de um dia e os preços utilizados nesta estimativa correspondem ao nível do mercado após decorrido tal prazo. Por outro lado, no caso do tamanho da carteira ser grande em relação aos volumes usualmente negociados no mercado, dois efeitos podem ocorrer dependendo da estratégia adotada ao se tentar zerá-la: (i) no caso de se procurar liquidá-la em um curto espaço de tempo, desloca-se os preços do mercado de modo a equilibrar a demanda com a oferta adicional que se gerou, ou (ii) alonga-se o tempo total para realizar tal liquidação, executando-a de forma paulatina. No primeiro caso, ou os ativos serão comprados a preços mais altos ou vendidos a preços mais baixos que aqueles normalmente utilizados no cálculo do VaR. No segundo caso, o horizonte de tempo utilizado para se zerar a carteira é maior que aquele utilizado no cálculo usual do VaR. Neste trabalho, utilizaremos uma abordagem de valores extremos para estimar a perda potencial total a que uma carteira está exposta, ou seja, a perda potencial considerando-se que ela é mantida durante um determinado horizonte de tempo de um dia, por exemplo - e que, a partir deste momento, realiza-se a sua liquidação de acordo com a liquidez do mercado, encerrando-se apenas uma fração da carteira a cada dia. Tal perda potencial será estimada com um nível de confiança elevado - 99.9%, por exemplo - o qual corresponde a eventos de crise.
Title in English
Calculating the value at risk of portfolios with large positions: an approach based on extreme value theory
Keywords in English
Capital markets
Finance
Risk management
Abstract in English
Usually, a portfolios Value at Risk (VaR) is estimated over a target horizon of one day and the prices used in this estimation are those which can be seen in the financial market after this period of time. On the other hand, if the size of the analyzed portfolio is large compared to the usual traded volumes, two effects can happen when we try to unwind the positions: (i) if we try to unwind them during a very short period of time, supply-demand curves are shifted so that the supply and the demand reach a new equilibrium, or (ii) we do it gradually and over a longer period of time. In the first case, the assets will be bought at higher prices or sold at lower prices than those they are usually traded at in the market. In the second case, the time spent to unwind the positions is longer than the one usually adopted to calculate the portfolios VaR. This paper uses an extreme value approach in order to estimate the total potential loss which a portfolio is exposed to, that is, the potential loss considering that it is kept for a specific period of time - of one day, for example - and, after that, its positions are unwind according to the markets liquidity. Hence, only a portfolios fraction is unwind at a day. Such potential loss is estimated at a high confidence level - of 99.9%, for instance - which corresponds to a crisis event.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2023-06-07
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.