Detalhes bibliográficos
| Ano de defesa: |
2016 |
| Autor(a) principal: |
Hernandez, Rafael Gonini |
| Orientador(a): |
Oliveira, Alexandre de |
| Banca de defesa: |
Não Informado pela instituição |
| Tipo de documento: |
Dissertação
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
por |
| Instituição de defesa: |
Não Informado pela instituição
|
| Programa de Pós-Graduação: |
Não Informado pela instituição
|
| Departamento: |
Não Informado pela instituição
|
| País: |
Não Informado pela instituição
|
| Palavras-chave em Português: |
|
| Palavras-chave em Inglês: |
|
| Link de acesso: |
http://hdl.handle.net/10438/17015
|
Resumo: |
The aim of this work is to analyze the use of alpha stable distribution modeling of financial series returns applied to the calculation of Value at Risk for market risk management. Besides used in many theories, the normal distribution may not be the most suitable to represent the empirical financial data, since many series presents leptokurtic behavior. As an alternative, it was analyzed the alpha stable distribution application, whose performance was compared with normal e t-student distributions through Kupiec’s, Christoffersen’s and Berkowitz’s backtests. Different types of assets were selected for the analysis, like PTAX and BOVESPA indexes, different maturities of the PREBRL tax and stocks negotiated at the Brazilian Stock Exchange BM&FBovespa. VaR was calculated for 95% and 99% confidence intervals. It was concluded for the analyzed series that, the higher the VaR confidence level is, better is the adequacy of leptokurtic distributions for parametric VaR modeling. |
