• 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.45.2010.tde-14062010-164451
Document
Author
Full name
Victor Sakimoto Shie
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2010
Supervisor
Committee
Chiann, Chang (President)
Alencar, Airlane Pereira
Marques, Guilherme de Oliveira Lima Cagliari
Title in Portuguese
Cointegração fracionária em séries financeiras
Keywords in Portuguese
Cointegração Fracionária Memória Longa
Abstract in Portuguese
O objetivo deste trabalho é apresentar alguns testes de cointegração fracionária para séries integradas de ordem d (dR), i.e., séries I(d), comparando-os com os testes de cointegração, cujo parâmetro d assume valores inteiros. O procedimento para os testes de cointegração fracionária utiliza reamostragens de bootstrap com reposição para gerar séries sob a hipótese nula de não cointegração. Estas reamostragens são então utilizadas para calcular os p-valores de algumas estatísticas de testes de regressão, tais como a estatística de Durbin-Watson e a estimativa do parâmetro de memória longa (d) residual. O poder destes testes é apresentado e comparado com os testes de cointegração, mostrando sua consistência. A aplicação destes testes a dados reais compara o modelo de correção de erros de cointegração com o modelo de correção de erros de cointegração fracionária utilizando a medida de erros quadráticos médios dos modelos ajustados.
Title in English
Fractional Cointegration in financial series
Keywords in English
fractional cointegration long memmory
Abstract in English
The purpose of this project is to present some fractional cointegration tests for integrated time series of order d (dR), i.e., I(d) time series, comparing them to cointegration tests, where the parameter d assumes integer values. The tests procedure is done by using bootstrap samples to obtain series under the null hypothesis of non-cointegration. These samples are then used to estimate the p-value of some regression-based test statistics, such as the Durbin-Watson statistic and estimates of residual d parameter. The application of these tests to real series compares the error correction model of cointegration to the error correction model of fractional cointegration by evaluating the mean squared errors over the residuals from the fitted models.
 
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.
Victor_Mestrado_r3.pdf (731.97 Kbytes)
Publishing Date
2011-01-05
 
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.