Publicação

Volatility forecasts and value-at-risk estimation using TGARCH model

Ver documento

Detalhes bibliográficos
Resumo:Value-at-Risk (VaR) has emerged in recent years as a standard tool to measure and control the risk, mainly the market risk, of financial portfolios. It measures the worst loss to be expected of a portfolio over a given time horizon at a given level of confidence. The calculation of Value-at-Risk commonly, involves estimation of the volatility return price and quantile of standardized returns. In this paper, two parametric techniques were used to estimate the volatility of the returns (market prices) of a Portuguese Financial Institution portfolio. Although to achieve the quantiles of standardized returns, both parametric technique and one nonparametric technique were considered. The quality of the measuring result was analysed through the backtesting technique for the forecasting multiperiod. In this study it is revealed that AR(1)-TGARCH methodology produces the most accurate VaR forecast, for one day holding period. The volatility forecasts for the two other holding periods, considering the three methodologies, revealed to be biased.
Autores principais:Ruivo, Sandra Cristina Rosa
Assunto:Market Risk Value-at-Risk Volatility Forecasting TGARCH Backtesting
Ano:2007
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade de Lisboa
Idioma:inglês
Origem:Repositório da Universidade de Lisboa
Descrição
Resumo:Value-at-Risk (VaR) has emerged in recent years as a standard tool to measure and control the risk, mainly the market risk, of financial portfolios. It measures the worst loss to be expected of a portfolio over a given time horizon at a given level of confidence. The calculation of Value-at-Risk commonly, involves estimation of the volatility return price and quantile of standardized returns. In this paper, two parametric techniques were used to estimate the volatility of the returns (market prices) of a Portuguese Financial Institution portfolio. Although to achieve the quantiles of standardized returns, both parametric technique and one nonparametric technique were considered. The quality of the measuring result was analysed through the backtesting technique for the forecasting multiperiod. In this study it is revealed that AR(1)-TGARCH methodology produces the most accurate VaR forecast, for one day holding period. The volatility forecasts for the two other holding periods, considering the three methodologies, revealed to be biased.