Plataforma Sucupira

Instituição de Ensino Superior:

UNIVERSIDADE FEDERAL DO RIO DE JANEIRO

Programa:

ESTATÍSTICA (31001017005P0)

Modalidade de Ensino:

Título:

Dynamic Graphical Models using Shrinkage Process Priors

Autor:

REBECCA DE OLIVEIRA SOUZA

Tipo de Trabalho de Conclusão:

TESE

Data Defesa:

06/05/2024

Resumo:

A ser preenchido

Palavras-Chave:

A ser preenchido

Abstract:

This overarching thesis presents innovative methodologies for estimating high dimensional time series data using graphical models. The content is divided into two main chapters, which are structured in the form of articles, supplemented by introductory and concluding chapters. The first article introduces the Dynamic Graphical Variable Selection model, which combines dynamic linear models with spike-and-slab priors for variable selection, allowing for the inference of connectivity in brain regions with varying weights and graphical structures over time. Demonstrating computational efficiency and competitiveness against prior methodologies in handling high-dimensional data, the model is illustrated through numerical experiments. The proposal is particularly appealing for research contributions, especially aimed at brain/cortical mapping related to cognitive issues. Similarly, the second article introduces the Dynamic Graphical Variable Selection for Directed Acyclic Graph model, employing a Dynamic Horseshoe Process for variable selection and incorporating an algorithm to search for directed acyclic graph structures. This approach demonstrates superior performance and increased flexibility in estimating networks for groups of individuals over time, as evidenced by simulated and real data experiments. The results suggest that our estimates outperform previous network search methodologies and demonstrate greater flexibility. Together, these articles contribute significant advancements to the understanding of brain connectivity dynamics, providing promising avenues for future research in neuroscience.

Keyword:

Dynamic Graphical Models;Probabilistic graphical models;Dynamic Variable Selection;Effective Connectivity;Brain Network

Volume:

1

Páginas:

125

Idioma:

INGLES

Biblioteca Depositária:

UNIVERSIDADE FEDERAL DO RIO DE JANEIRO

Autorização de divulgação:

O trabalho possui divulgação autorizada

Área de Concentração:

ESTATÍSTICA

Linha de Pesquisa:

MODELOS HIERÁRQUICOS E DINÂMICOS

Projeto de Pesquisa:

MODELOS HIERÁRQUICOS: TEORIA E APLICAÇÃO

Orientador:

MARINA SILVA PAEZ

Categoria:

DOCENTE - PERMANENTE

O orientador principal compôs a banca do discente?

Sim


Nome	Categoria
DIEGO CARVALHO DO NASCIMENTO	Participante Externo
MARINA SILVA PAEZ	Docente - PERMANENTE
ANDERSON LUIZ ARA SOUZA	Participante Externo
DANI GAMERMAN	Docente - PERMANENTE
GUILHERME OST DE AGUIAR	Docente - PERMANENTE

Tipo de Vínculo Empregatício:

Colaborador

Tipo de Instituição:

Empresa Pública ou Estatal

Expectativa de Atuação:

Ensino e Pesquisa

Mesma Área de Atuação:

Sim

Plataforma Sucupira

Dados do Trabalhos de Conclusão

Contexto

Banca Examinadora

Vínculo