• 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.104.2024.tde-02042024-143434
Document
Author
Full name
Bruno Estanislau Holtz
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2024
Supervisor
Committee
Ehlers, Ricardo Sandes (President)
Abanto-valle, Carlos Antonio
Laurini, Marcio Poletti
Title in Portuguese
Inferência Bayesiana em modelos de volatilidade estocástica na média utilizando o método de Monte Carlo Hamiltoniano em variedade Riemanniana
Keywords in Portuguese
Distribuição mistura de escala normal
Modelo de volatilidade estocástica na média
Monte Carlo hamiltoniano
Monte Carlo hamiltoniano em variedade riemanniana
Séries financeiras
Abstract in Portuguese
Este trabalho considera o modelo de volatilidade estocástica na média, no qual a distribuição condicional dos dados pertence a família mistura de escala normal para modelagem de séries financeiras. Esta classe de modelos é mais robusta por acomodar erros com caudas mais pesadas que a distribuição normal, visto que esta é uma característica marcante de séries financeiras. Para a estimativa dos parâmetros, propomos um algoritmo Bayesiano via cadeias de Markov, utilizando o método Monte Carlo Hamiltoniano (HMC) e sua variante, o método Monte Carlo Hamiltoniano em Variedade Riemanniana (RMHMC). O algoritmo foi implementado utilizando as bibliotecas Rcpp e RcppArmadillo disponíveis na linguagem R. Os critérios de informação recentemente desenvolvidos, Watanabe Akaike Information Criterion (WAIC) e Leave-One-Out Cross-Validation (LOO-CV) foram calculados para comparar o ajuste dos modelos, bem como o Deviance Information Criterion (DIC). Estudos de simulação foram realizados para ilustrar e avaliar o desempenho do método proposto. Por fim, realizamos aplicações a dados reais, fornecendo evidências empíricas de sua efetividade.
Title in English
Bayesian inference in stochastic volatility in mean model using Riemannian manifold Hamiltonian Monte Carlo method
Keywords in English
Financial series
Hamiltonian Monte Carlo
Riemannian manifold hamiltonian Monte Carlo
Scale mixture of normal
Stochastic volatility in mean model
Abstract in English
This paper considers the stochastic volatility in mean model, where the conditional distribution of the data belongs to the mixed-scale normal family for modeling financial time series. This model class is more robust in accommodating errors with heavier tails than the normal distribution, a characteristic often observed in financial data. Parameter estimation is conducted through a Bayesian algorithm employing Markov Chain methods, specifically the Hamiltonian Monte Carlo (HMC) method and its variant, the Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) method. The algorithm is implemented using the Rcpp and RcppArmadillo libraries in the R language. Recently developed information criteria, namely the Watanabe Akaike Information Criterion (WAIC) and leave-one-out cross-validation (LOO-CV), along with the deviance information criterion (DIC), are calculated to compare the model fits. Simulation studies are conducted to illustrate and evaluate the performance of the proposed method. Finally, we apply the developed methodology to real return series, providing empirical evidence of its effectiveness.
 
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
2024-04-02
 
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.