Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study

Detalhes bibliográficos
Autor(a) principal: Varmann, Lauri
Data de Publicação: 2022
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10451/54256
Resumo: Tese de mestrado, Bioestatística, 2022, Universidade de Lisboa, Faculdade de Ciências
id RCAP_63712f639e923b5d90f731c5d5d96748
oai_identifier_str oai:repositorio.ul.pt:10451/54256
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation StudyProcesso de ramificação Galton-Watsonagrupamento hierárquicobootstrap não paramétricosimulaçãodistância de transferênciaTeses de mestrado - 2022Departamento de Estatística e Investigação OperacionalTese de mestrado, Bioestatística, 2022, Universidade de Lisboa, Faculdade de CiênciasRecently there have been published several works that focus on clustering based on infectious disease data (e.g., Maugeri et al., 2020; Mahmoudi et al., 2020; Zarikas et al., 2020). These studies did not use the effective reproduction number in their clustering method, did not consider different types of infected individuals and the problem of ties in clustering was not thoroughly addressed. We develop a method to cluster regions based on infectious disease type-specific prevalence and typespecific reproduction numbers. To incorporate these two characteristics into one formula, the beginning of an epidemic is modelled by a two-type Galton-Watson branching process model. We define the model parameter as the expected number of total infections arising in a finite number of generations from one infected individual whose type is unknown. Nonparametric bootstrap is used for estimation of the model parameter. Empirical bootstrap distributions of the model parameter are then clustered using the supremum distance and variable-group hierarchical agglomerative single linkage clustering technique. By doing a simulation study, we examined how well the clusters obtained by bootstrap sampling distributions resemble the clusters obtained by using transformed multinomial distributions as a reference. Using the scaled version of the transfer distance as the performance measure, we found that the best performance was observed in scenarios where the prevalence was uniformly distributed, the sample size was 500 and two clusters were retained. Problematic ties occurred in approximately 0,5% of the simulations. The results suggest that our method performs well in some circumstances. When there is a large proportion of countries with low disease prevalence, the number of individuals sampled in each country should be increased. Besides that, if there is not an important reason to prefer to retain four clusters, then three or preferably two clusters should be retained to get better performance.Nunes, Maria Helena Mouriño Silva, 1969-Repositório da Universidade de LisboaVarmann, Lauri202220222024-05-30T00:00:00Z2022-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10451/54256enginfo:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-08T17:00:40Zoai:repositorio.ul.pt:10451/54256Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:05:10.158815Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
title Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
spellingShingle Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
Varmann, Lauri
Processo de ramificação Galton-Watson
agrupamento hierárquico
bootstrap não paramétrico
simulação
distância de transferência
Teses de mestrado - 2022
Departamento de Estatística e Investigação Operacional
title_short Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
title_full Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
title_fullStr Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
title_full_unstemmed Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
title_sort Hierarchical Clustering Based on a Two-Type Branching Process Model: A Simulation Study
author Varmann, Lauri
author_facet Varmann, Lauri
author_role author
dc.contributor.none.fl_str_mv Nunes, Maria Helena Mouriño Silva, 1969-
Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Varmann, Lauri
dc.subject.por.fl_str_mv Processo de ramificação Galton-Watson
agrupamento hierárquico
bootstrap não paramétrico
simulação
distância de transferência
Teses de mestrado - 2022
Departamento de Estatística e Investigação Operacional
topic Processo de ramificação Galton-Watson
agrupamento hierárquico
bootstrap não paramétrico
simulação
distância de transferência
Teses de mestrado - 2022
Departamento de Estatística e Investigação Operacional
description Tese de mestrado, Bioestatística, 2022, Universidade de Lisboa, Faculdade de Ciências
publishDate 2022
dc.date.none.fl_str_mv 2022
2022
2022-01-01T00:00:00Z
2024-05-30T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10451/54256
url http://hdl.handle.net/10451/54256
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/embargoedAccess
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134603382882304