• 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.55.2018.tde-24012018-112732
Document
Author
Full name
Valeria Aparecida Martins Ferreira
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2001
Supervisor
Committee
Andrade Filho, Marinho Gomes de (President)
Carvalho, André Carlos Ponce de Leon Ferreira de
Reisen, Valderio Anselmo
Title in Portuguese
Uso de MCMC na abordagem Bayesiana de modelos ARCH e GARCH
Keywords in Portuguese
Não disponível
Abstract in Portuguese
Neste trabalho é descrito uma seqüência de procedimentos para estimar parâmetros e selecionar ordem de modelos Auto-Regressivos com heterocedasticidade, ARCH(p), e Auto- Regressivos generalizados, GARCH(p,q). As estimativas são obtidas utilizando duas técnicas: a inferência clássica e a bayesiana em conjunto com simulação de Monte Carlo em Cadeia de Markov (MCMC). Na análise bayesiana utilizamos densidades a priori normais para os parâmetros do modelo. Os métodos desenvolvidos foram aplicados em duas séries geradas e em três séries do mercado financeiro: Índice Bovespa, Telebrás e Cotação em Dólar Americano da moeda Iene Japonês. Em geral, as estimativas de máxima verossimilhança e bayesiana apresentaram resultados próximos. Porém, em algumas séries, o intervalo com 95% de confiança para certos parâmetros do modelo apresentou valores negativos, o que viola as restrições impostas aos parâmetros dos modelos ARCH(p), destacando a vantagem da abordagem bayesiana.
Title in English
Not available
Keywords in English
Not available
Abstract in English
In this work a sequence of procedures is described to estimate parameters, to select order and to forecast Autoregressive Conditional Heteroskedasticity ARCH(p) and generalized ARCH, GARCH(p,q), modeis. The estimates are obtained by using both classical inference techniques via maximum likelihood estimation and Bayesian inference approach jointly with simulation of Monte Cano Markov Chain (MCMC). In the Bayesian analysis we use normal prior densities for the parameters of the model. The applications for the developed methods were made in a generated series and iii three series of the Brazilian finance market: Index Bovespa, Telebrás and Quotation in American Doilar of the Japanese Yen. In general, the maximum likelihood and Bayesian estimates are similar. However, in some series, the 95% confidence intervais for some parameters of the model, presented negative values, violating the constraints imposed to the parameters of the ARCH(p) modeis, highlighting certain advantage of the Bayesian approach.
 
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
2018-01-24
 
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.