Master's Dissertation
DOI
https://doi.org/10.11606/D.12.2005.tde-23062022-112228
Document
Author
Full name
Rafael Machado Santana
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2005
Supervisor
Committee
Bueno, Rodrigo de Losso da Silveira (President)
Alves, Denisard Cneio de Oliveira
Pinto, Afonso de Campos
Title in Portuguese
SWARCH e volatilidade implícita na taxa de câmbio REAL/USD
Keywords in Portuguese
Análise de séries temporais
Câmbio (Economia)
Opções financeiras
Taxa de câmbio
Abstract in Portuguese
Este trabalho faz uma comparação empírica entre previsões da volatilidade do retomo da taxa de câmbio entre o real e o dólar, obtidas por meio de um modelo de séries temporais com mudança de regime na variância condicional, o SWARCH de Hamilton e Susmel (1994), e da volatilidade implícita nos preços de opções sobre aquele ativo, negociadas na Bolsa de Mercadorias e Futuros de São Paulo (BM&F). A comparação é feita por meio de regressões que avaliam o poder de predição e o conteúdo informacional das previsões. Os resultados apontam que considerar distintos estados para a volatilidade do retorno da taxa de câmbio faz com que o desempenho do modelo de série de tempo seja melhor do que o da volatilidade implícita, produzindo, dessa forma, resultados inversos aos constatados na literatura, onde se utilizam especificações sem mudança de regime, como o GARCH
Title in English
SWARCH and implied volatility in the REAL/USD exchange rate
Keywords in English
Exchange (Economics)
Exchange rate
Financial options
Time series analysis
Abstract in English
This article evaluates empirically the performance of two approaches for predicting the volatility of REAL/USD exchange rate return, one of those using a time series model with conditional variance subject to regime switch, the SWARCH model of Hamilton and Susmel (1994), and the other one based on the volatility implied in the price of options quoted at the Bolsa de Mercadorias e Futuros de São Paulo (BM&F). The comparison between those two approaches relies on regression based tests of predictive ability and informational content. The results show that the use of a time series model with distinct regimes of volatilityfor the return of the exchange rate outperforms the forecast obtained by implied volatility, contradicting, therefore, the evidences pointed out in the literature obtained with time series models with no regime switch in variance, such as GARCH
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
2022-06-23