Distribution‑free multiple imputation in incomplete two‑way tables
Autor(a) principal: | |
---|---|
Data de Publicação: | 2014 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Pesquisa Agropecuária Brasileira (Online) |
Texto Completo: | https://seer.sct.embrapa.br/index.php/pab/article/view/19358 |
Resumo: | The objective of this work was to propose a new distribution‑free multiple imputation algorithm, through modifications of the simple imputation method recently developed by Yan in order to circumvent the problem of unbalanced experiments. The method uses the singular value decomposition of a matrix and was tested using simulations based on two complete matrices of real data, obtained from eucalyptus and sugarcane trials, with values deleted randomly at different percentages. The quality of the imputations was evaluated by a measure of overall accuracy that combines the variance between imputations and their mean square deviations in relation to the deleted values. The best alternative for multiple imputation is a multiplicative model that includes weights near to 1 for the eigenvalues calculated with the decomposition. The proposed methodology does not depend on distributional or structural assumptions and does not have any restriction regarding the pattern or the mechanism of the missing data. |
id |
EMBRAPA-4_525ea5e4619feeda4ecc493d3438dec1 |
---|---|
oai_identifier_str |
oai:ojs.seer.sct.embrapa.br:article/19358 |
network_acronym_str |
EMBRAPA-4 |
network_name_str |
Pesquisa Agropecuária Brasileira (Online) |
repository_id_str |
|
spelling |
Distribution‑free multiple imputation in incomplete two‑way tablesImputação múltipla livre de distribuição em tabelas incompletas de dupla entradamissing data; singular value decomposition; multi‑environment trials; unbalanced experiments; genotype x environment interaction; plant breedingdados ausentes; decomposição por valores singulares; ensaios multiambiente; experimentos desbalanceados; interação genótipo x ambiente; melhoramento de plantasThe objective of this work was to propose a new distribution‑free multiple imputation algorithm, through modifications of the simple imputation method recently developed by Yan in order to circumvent the problem of unbalanced experiments. The method uses the singular value decomposition of a matrix and was tested using simulations based on two complete matrices of real data, obtained from eucalyptus and sugarcane trials, with values deleted randomly at different percentages. The quality of the imputations was evaluated by a measure of overall accuracy that combines the variance between imputations and their mean square deviations in relation to the deleted values. The best alternative for multiple imputation is a multiplicative model that includes weights near to 1 for the eigenvalues calculated with the decomposition. The proposed methodology does not depend on distributional or structural assumptions and does not have any restriction regarding the pattern or the mechanism of the missing data.O objetivo deste trabalho foi propor um novo algoritmo de imputação múltipla livre de distribuição, por meio de modificações no método de imputação simples recentemente desenvolvido por Yan para contornar o problema de desbalanceamento de experimentos. O método utiliza a decomposição por valores singulares de uma matriz e foi testado por meio de simulações baseadas em duas matrizes de dados reais completos, provenientes de ensaios com eucalipto e cana‑de‑açúcar, com retiradas aleatórias de valores em diferentes percentagens. A qualidade das imputações foi avaliada por uma medida de acurácia geral que combina a variância entre imputações e o viés quadrático médio delas em relação aos valores retirados. A melhor alternativa para imputação múltipla é um modelo multiplicativo que inclui pesos próximos a 1 para os autovalores calculados com a decomposição. A metodologia proposta não depende de pressuposições distribucionais ou estruturais e não tem restrições quanto ao padrão ou ao mecanismo de ausência dos dados.Pesquisa Agropecuaria BrasileiraPesquisa Agropecuária BrasileiraCAPESCNPqTWASArciniegas-Alarcón, SergioDias, Carlos Tadeu dos SantosGarcía-Peña, Marisol2014-10-20info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://seer.sct.embrapa.br/index.php/pab/article/view/19358Pesquisa Agropecuaria Brasileira; v.49, n.9, set. 2014; 683-691Pesquisa Agropecuária Brasileira; v.49, n.9, set. 2014; 683-6911678-39210100-104xreponame:Pesquisa Agropecuária Brasileira (Online)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPAporhttps://seer.sct.embrapa.br/index.php/pab/article/view/19358/12786https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/19358/11678https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/19358/11679info:eu-repo/semantics/openAccess2014-10-20T19:27:26Zoai:ojs.seer.sct.embrapa.br:article/19358Revistahttp://seer.sct.embrapa.br/index.php/pabPRIhttps://old.scielo.br/oai/scielo-oai.phppab@sct.embrapa.br || sct.pab@embrapa.br1678-39210100-204Xopendoar:2014-10-20T19:27:26Pesquisa Agropecuária Brasileira (Online) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false |
dc.title.none.fl_str_mv |
Distribution‑free multiple imputation in incomplete two‑way tables Imputação múltipla livre de distribuição em tabelas incompletas de dupla entrada |
title |
Distribution‑free multiple imputation in incomplete two‑way tables |
spellingShingle |
Distribution‑free multiple imputation in incomplete two‑way tables Arciniegas-Alarcón, Sergio missing data; singular value decomposition; multi‑environment trials; unbalanced experiments; genotype x environment interaction; plant breeding dados ausentes; decomposição por valores singulares; ensaios multiambiente; experimentos desbalanceados; interação genótipo x ambiente; melhoramento de plantas |
title_short |
Distribution‑free multiple imputation in incomplete two‑way tables |
title_full |
Distribution‑free multiple imputation in incomplete two‑way tables |
title_fullStr |
Distribution‑free multiple imputation in incomplete two‑way tables |
title_full_unstemmed |
Distribution‑free multiple imputation in incomplete two‑way tables |
title_sort |
Distribution‑free multiple imputation in incomplete two‑way tables |
author |
Arciniegas-Alarcón, Sergio |
author_facet |
Arciniegas-Alarcón, Sergio Dias, Carlos Tadeu dos Santos García-Peña, Marisol |
author_role |
author |
author2 |
Dias, Carlos Tadeu dos Santos García-Peña, Marisol |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
CAPES CNPq TWAS |
dc.contributor.author.fl_str_mv |
Arciniegas-Alarcón, Sergio Dias, Carlos Tadeu dos Santos García-Peña, Marisol |
dc.subject.por.fl_str_mv |
missing data; singular value decomposition; multi‑environment trials; unbalanced experiments; genotype x environment interaction; plant breeding dados ausentes; decomposição por valores singulares; ensaios multiambiente; experimentos desbalanceados; interação genótipo x ambiente; melhoramento de plantas |
topic |
missing data; singular value decomposition; multi‑environment trials; unbalanced experiments; genotype x environment interaction; plant breeding dados ausentes; decomposição por valores singulares; ensaios multiambiente; experimentos desbalanceados; interação genótipo x ambiente; melhoramento de plantas |
description |
The objective of this work was to propose a new distribution‑free multiple imputation algorithm, through modifications of the simple imputation method recently developed by Yan in order to circumvent the problem of unbalanced experiments. The method uses the singular value decomposition of a matrix and was tested using simulations based on two complete matrices of real data, obtained from eucalyptus and sugarcane trials, with values deleted randomly at different percentages. The quality of the imputations was evaluated by a measure of overall accuracy that combines the variance between imputations and their mean square deviations in relation to the deleted values. The best alternative for multiple imputation is a multiplicative model that includes weights near to 1 for the eigenvalues calculated with the decomposition. The proposed methodology does not depend on distributional or structural assumptions and does not have any restriction regarding the pattern or the mechanism of the missing data. |
publishDate |
2014 |
dc.date.none.fl_str_mv |
2014-10-20 |
dc.type.none.fl_str_mv |
|
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://seer.sct.embrapa.br/index.php/pab/article/view/19358 |
url |
https://seer.sct.embrapa.br/index.php/pab/article/view/19358 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://seer.sct.embrapa.br/index.php/pab/article/view/19358/12786 https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/19358/11678 https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/19358/11679 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Pesquisa Agropecuaria Brasileira Pesquisa Agropecuária Brasileira |
publisher.none.fl_str_mv |
Pesquisa Agropecuaria Brasileira Pesquisa Agropecuária Brasileira |
dc.source.none.fl_str_mv |
Pesquisa Agropecuaria Brasileira; v.49, n.9, set. 2014; 683-691 Pesquisa Agropecuária Brasileira; v.49, n.9, set. 2014; 683-691 1678-3921 0100-104x reponame:Pesquisa Agropecuária Brasileira (Online) instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa) instacron:EMBRAPA |
instname_str |
Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
instacron_str |
EMBRAPA |
institution |
EMBRAPA |
reponame_str |
Pesquisa Agropecuária Brasileira (Online) |
collection |
Pesquisa Agropecuária Brasileira (Online) |
repository.name.fl_str_mv |
Pesquisa Agropecuária Brasileira (Online) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
repository.mail.fl_str_mv |
pab@sct.embrapa.br || sct.pab@embrapa.br |
_version_ |
1793416701649354752 |