Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.6/10484 |
Resumo: | Almost all quantitative studies in educational assessment, evaluation and educational research are based on incomplete data sets, which have been a problem for years without a single solution. The use of big identifiable data poses new challenges in dealing with missing values. In the first part of this paper, we present the state-of-art of the topic in the Brazilian education scientific literature, and how researchers have dealt with missing data since the turn of the century. Next, we use open access software to analyze real-world data, the 2017 Prova Brasil , for several federation units to document how the naïve assumption of missing completely at random may substantially affect statistical conclusions, researcher interpretations, and subsequent implications for policy and practice. We conclude with straightforward suggestions for any education researcher on applying R routines to conduct the hypotheses test of missing completely at random and, if the null hypothesis is rejected, then how to implement the multiple imputation, which appears to be one of the most appropriate methods for handling missing data. |
id |
RCAP_e13b79e2396f1d3fac07a2456c2d3609 |
---|---|
oai_identifier_str |
oai:ubibliorum.ubi.pt:10400.6/10484 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment systemProva BrasilMissing dataRMultiple imputationAlmost all quantitative studies in educational assessment, evaluation and educational research are based on incomplete data sets, which have been a problem for years without a single solution. The use of big identifiable data poses new challenges in dealing with missing values. In the first part of this paper, we present the state-of-art of the topic in the Brazilian education scientific literature, and how researchers have dealt with missing data since the turn of the century. Next, we use open access software to analyze real-world data, the 2017 Prova Brasil , for several federation units to document how the naïve assumption of missing completely at random may substantially affect statistical conclusions, researcher interpretations, and subsequent implications for policy and practice. We conclude with straightforward suggestions for any education researcher on applying R routines to conduct the hypotheses test of missing completely at random and, if the null hypothesis is rejected, then how to implement the multiple imputation, which appears to be one of the most appropriate methods for handling missing data.Quase todos os estudos quantitativos em aferição, avaliação e pesquisa educacional são baseados em conjuntos de dados incompletos, que têm sido um problema há anos sem solução única. O uso de grandes dados identificáveis apresenta novos desafios para lidar com valores ausentes. Na primeira parte deste artigo, apresentamos o estado-da-arte do tópico na literatura científica educacional brasileira e como os pesquisadores têm tratado os dados omissos. Em seguida, usamos o software de acesso livre para analisar dados do mundo real, a Prova Brasil 2017, para várias unidades da federação, e documentamos como pressuposto de dados omissos completamente aleatórios pode afetar os resultados estatísticos, as interpretações e implicações subsequentes para políticas e práticas. Concluímos com sugestões diretas para qualquer pesquisador de Educação sobre a aplicação de rotinas R para realizar o teste de hipóteses de dados omissos completamente aleatórios e, se a hipótese nula for rejeitada, como implementar a imputação múltipla, que parece ser um dos métodos mais apropriados para manipular dados ausentes.Casi todos los estudios cuantitativos en evaluación, evaluación e investigación educativa se basan en conjuntos de datos incompletos, que han sido un problema desde hace años sin solución única. El uso de grandes datos identificables presenta nuevos desafíos para manejar los valores ausentes. En la primera parte de este artículo, presentamos el estado del arte del tópico en la literatura científica educativa brasileña y cómo los investigadores han tratado los datos omisos. A continuación, utilizamos el software de acceso libre para analizar datos del mundo real, la Prueba Brasil 2017, para varias unidades de la federación, y documentamos cómo la asunción de datos omisos completamente aleatorios puede afectar los resultados estadísticos, las interpretaciones e implicaciones subsecuentes para políticas y prácticas. Concluimos con sugerencias directas para cualquier investigador de Educación sobre la aplicación de rutinas R para realizar la prueba de hipótesis de datos omisos completamente aleatorios y, si la hipótesis nula es rechazada, cómo implementar la imputación múltiple, que parece ser uno de los métodos más apropiados para manipular datos ausentes.Centro-01-0145-FEDER-000019-C4-Centro de Competências em Cloud Computing and by the Brazilian Coordination for the Improvement of Higher Education Personnel Foundation, through a post-doc fellowship for a research project, which took place at the Faculty of Sciences of the University of Beira Interior, Portugal (Capes-PVE88881.169888/2018-01), and partially supported by the Brazilian National Council for Scientific and Technological Development (CNPq-process 440172 / 2017-9).ScielouBibliorumFerrão, Maria EugéniaPrata, PaulaAlves, Maria Teresa G.2020-10-26T09:41:00Z20202020-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.6/10484engFerrão, Maria Eugénia, Prata, Paula, & Alves, Maria Teresa Gonzaga. (2020). Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system. Ensaio: Avaliação e Políticas Públicas em Educação, 28(108), 599-621. Epub May 08, 2020.https://doi.org/10.1590/s0104-4036202000280234610.1590/s0104-40362020002802346info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-12-15T09:52:20Zoai:ubibliorum.ubi.pt:10400.6/10484Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:50:25.725288Repositório 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 |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system |
title |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system |
spellingShingle |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system Ferrão, Maria Eugénia Prova Brasil Missing data R Multiple imputation |
title_short |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system |
title_full |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system |
title_fullStr |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system |
title_full_unstemmed |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system |
title_sort |
Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system |
author |
Ferrão, Maria Eugénia |
author_facet |
Ferrão, Maria Eugénia Prata, Paula Alves, Maria Teresa G. |
author_role |
author |
author2 |
Prata, Paula Alves, Maria Teresa G. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
uBibliorum |
dc.contributor.author.fl_str_mv |
Ferrão, Maria Eugénia Prata, Paula Alves, Maria Teresa G. |
dc.subject.por.fl_str_mv |
Prova Brasil Missing data R Multiple imputation |
topic |
Prova Brasil Missing data R Multiple imputation |
description |
Almost all quantitative studies in educational assessment, evaluation and educational research are based on incomplete data sets, which have been a problem for years without a single solution. The use of big identifiable data poses new challenges in dealing with missing values. In the first part of this paper, we present the state-of-art of the topic in the Brazilian education scientific literature, and how researchers have dealt with missing data since the turn of the century. Next, we use open access software to analyze real-world data, the 2017 Prova Brasil , for several federation units to document how the naïve assumption of missing completely at random may substantially affect statistical conclusions, researcher interpretations, and subsequent implications for policy and practice. We conclude with straightforward suggestions for any education researcher on applying R routines to conduct the hypotheses test of missing completely at random and, if the null hypothesis is rejected, then how to implement the multiple imputation, which appears to be one of the most appropriate methods for handling missing data. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-10-26T09:41:00Z 2020 2020-01-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.6/10484 |
url |
http://hdl.handle.net/10400.6/10484 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Ferrão, Maria Eugénia, Prata, Paula, & Alves, Maria Teresa Gonzaga. (2020). Multiple imputation in big identifiable data for educational research: An example from the Brazilian education assessment system. Ensaio: Avaliação e Políticas Públicas em Educação, 28(108), 599-621. Epub May 08, 2020.https://doi.org/10.1590/s0104-40362020002802346 10.1590/s0104-40362020002802346 |
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 |
Scielo |
publisher.none.fl_str_mv |
Scielo |
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_ |
1799136394689380352 |