Full text
| |
| Author(s): |
Daniel de Almeida
Total Authors: 1
|
| Document type: | Master's Dissertation |
| Press: | Campinas, SP. |
| Institution: | Universidade Estadual de Campinas (UNICAMP). Instituto de Matemática, Estatística e Computação Científica |
| Defense date: | 2013-07-31 |
| Examining board members: |
Luiz Koodi Hotta;
Mauricio Enrique Zevallos Herencia;
Ricardo Sandes Ehlers
|
| Advisor: | Luiz Koodi Hotta |
| Abstract | |
The objective of this dissertation is to study volatility models that consider two types of asymmetry usually found in finance series, the skewness of the innovations and the leverage effect. Skewness means that the distribution of losses has a heavier tail than the distribution of gains. The leverage effect stems from the fact that losses have a greater influence on future volatilities than gains. It is considered univariate GARCH models that include both types of asymmetry, separately and jointly, and multivariate GARCH models that allow for leverage effects. The results are presented in two papers. The first one describes the main univariate models that consider these two stylized facts and analyzes, in detail, eight series: the Ibovespa, Nasdaq and S&P 500 indices, and the Itaú-Unibanco, Vale, Petrobras, Banco do Brasil and Bradesco stocks. The conclusion is that both stylized facts are present in some series, mostly simultaneously. The second paper reviews the main multivariate GARCH models, including models with asymmetric effects on conditional variances and covariance. Some of these models are analyzed in more detail through simulations. The most used models in the literature are applied to a three-dimensional time series, containing the Bovespa index and the Petrobras and Vale markets. The three models selected by AIC and BIC criteria allow for leverage effects (AU) | |
| FAPESP's process: | 11/02881-9 - Asymmetries in volatility and perturbations in volatility models |
| Grantee: | Daniel de Almeida |
| Support Opportunities: | Scholarships in Brazil - Master |