IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS
Autor(a) principal: | |
---|---|
Data de Publicação: | 2024 |
Outros Autores: | , , |
Tipo de documento: | preprint |
Idioma: | por |
Título da fonte: | SciELO Preprints |
Texto Completo: | https://preprints.scielo.org/index.php/scielo/preprint/view/6097 |
Resumo: | This multidisciplinary work proposes new perspectives and reflections on the data from the multifaceted reality of Brazilian education. It was based on a meticulous methodology of unsupervised exploratory analysis, without any expectation of results, in order to allow the emergence of new insights spontaneously from the data. Special attention was given to data visualization in a multidimensional context, as a way to sensorially highlight the most immanent patterns, without compromising statistical rigor. Therefore, the main objective of this research was to create an innovative intertwining of techniques that, in the context of educational data, would offer more opportunities for questions and inquiries than answers. The database consisted of the Basic Education Development Index (Ideb) and the School Census, within a scope limited to elementary education in 58,920 public schools across Brazil. At the heart of the methodology was a Gaussian Copula paired with a recursive Factor Analysis, after careful treatment of missing values, outliers, linear dependencies, and feature selection. As a result, a plurality of patterns was obtained, both known from the literature and unprecedented. Like Ideb having weight in more than one dimension, implying a heterogeneity of associations involving this index, the infrastructure attributes, and the federal units. In conclusion, the methodology has shown to be reliable and robust in the challenge of composing new analytical perspectives on educational data, enabling the expansion of the scope in future studies. |
id |
SCI-1_634a6046c44ce178414f95a971b406a2 |
---|---|
oai_identifier_str |
oai:ops.preprints.scielo.org:preprint/6097 |
network_acronym_str |
SCI-1 |
network_name_str |
SciELO Preprints |
repository_id_str |
|
spelling |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSISIDEB, LAS UNIDADES FEDERATIVAS Y EL CENSO ESCOLAR: UN ANÁLISIS NO SUPERVISADOIDEB, AS UNIDADES FEDERATIVAS E O CENSO ESCOLAR: UMA ANÁLISE NÃO SUPERVISIONADAIndicadores educacionaisensino fundamentalanálise exploratória de dadosmodelos não supervisionadosEducational indicatorselementary educationexploratory data analysisunsupervised modelsIndicadores educativoseducación primariaanálisis exploratorio de datosmodelos no supervisadosThis multidisciplinary work proposes new perspectives and reflections on the data from the multifaceted reality of Brazilian education. It was based on a meticulous methodology of unsupervised exploratory analysis, without any expectation of results, in order to allow the emergence of new insights spontaneously from the data. Special attention was given to data visualization in a multidimensional context, as a way to sensorially highlight the most immanent patterns, without compromising statistical rigor. Therefore, the main objective of this research was to create an innovative intertwining of techniques that, in the context of educational data, would offer more opportunities for questions and inquiries than answers. The database consisted of the Basic Education Development Index (Ideb) and the School Census, within a scope limited to elementary education in 58,920 public schools across Brazil. At the heart of the methodology was a Gaussian Copula paired with a recursive Factor Analysis, after careful treatment of missing values, outliers, linear dependencies, and feature selection. As a result, a plurality of patterns was obtained, both known from the literature and unprecedented. Like Ideb having weight in more than one dimension, implying a heterogeneity of associations involving this index, the infrastructure attributes, and the federal units. In conclusion, the methodology has shown to be reliable and robust in the challenge of composing new analytical perspectives on educational data, enabling the expansion of the scope in future studies.Este trabajo multidisciplinario propone nuevas perspectivas y reflexiones sobre los datos de la realidad multifacética educativa brasileña. Se basó en una meticulosa metodología de análisis exploratorio no supervisado, sin expectativas de resultados, para permitir que lo nuevo emergiera espontáneamente a partir de los datos. Se prestó especial atención a la visualización de datos en un contexto multidimensional, como forma de resaltar sensorialmente los patrones más inminentes, sin comprometer el rigor estadístico. Por lo tanto, el objetivo principal de esta investigación fue componer un entrelazamiento innovador de técnicas que ofrecieran, en el contexto de los datos educativos, más oportunidades para preguntas y consultas que para respuestas. La base de datos consistió en el Índice de Desarrollo de la Educación Básica (Ideb) y el Censo Escolar, en un ámbito cerrado a la educación básica en 58.920 escuelas públicas de todo Brasil. En el centro de la metodología se encontraba una Cópula Gaussiana combinada con un Análisis Factorial recursivo, después de un tratamiento cuidadoso de los valores faltantes, los valores atípicos, las dependencias lineales y la selección de características. Como resultado, se obtuvo una pluralidad de patrones, tanto conocidos de la literatura como inéditos. Por ejemplo, el Ideb con peso en más de una dimensión, implicando una heterogeneidad de asociaciones que involucran este índice, los atributos de infraestructura y las unidades federativas. Se concluye que la metodología fue confiable y robusta en el desafío de componer nuevas perspectivas analíticas sobre los datos educativos, permitiendo incluso ampliar su alcance en futuros estudios.Este trabalho multidisciplinar propõe novos olhares e reflexões sobre os dados da multifacetada realidade educacional brasileira. Baseou-se numa criteriosa metodologia de análise exploratória não supervisionada, sem expectativa de resultados, de modo a dar chance ao novo de emergir espontaneamente a partir dos dados. Atenção especial recebeu a visualização de dados num contexto multidimensional, como forma de destacar sensorialmente os padrões mais imanentes, sem comprometimento do rigor estatístico. Logo, tal pesquisa teve como principal objetivo compor um entrelaçamento inovador de técnicas que oferecessem, no contexto de dados educacionais, mais oportunidades para perguntas e questionamentos que respostas. A base de dados consistiu no Índice de Desenvolvimento da Educação Básica (Ideb) e no Censo Escolar, num escopo fechado no ensino fundamental de 58920 escolas públicas de todo Brasil. No centro da metodologia esteve uma Cópula Gaussiana casada com uma Análise Fatorial recursiva, após cuidadoso tratamento de valores ausentes, valores extremos, dependências lineares e seleção de atributos. Como resultado, obteve-se uma pluralidade de padrões, tanto conhecidos da literatura, como inéditos. A exemplo do Ideb com peso em mais de uma dimensão, implicando em heterogeneidade de associações envolvendo este índice, os atributos de infraestrutura e as unidades da federação. Conclui-se que a metodologia foi confiável e robusta no desafio de compor novas perspectivas de análise sobre dados educacionais, viabilizando inclusive a ampliação do escopo em estudos futuros.SciELO PreprintsSciELO PreprintsSciELO Preprints2024-03-01info:eu-repo/semantics/preprintinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://preprints.scielo.org/index.php/scielo/preprint/view/609710.1590/SciELOPreprints.6097porhttps://preprints.scielo.org/index.php/scielo/article/view/6097/15239Copyright (c) 2023 Carlos Silveira, Igor Alvez, Rodrigo Jesus, João Romanellihttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessAlves, IgorJesus, RodrigoRomanelli, JoãoSilveira, Carlosreponame:SciELO Preprintsinstname:Scientific Electronic Library Online (SCIELO)instacron:SCI2023-05-16T16:36:44Zoai:ops.preprints.scielo.org:preprint/6097Servidor de preprintshttps://preprints.scielo.org/index.php/scieloONGhttps://preprints.scielo.org/index.php/scielo/oaiscielo.submission@scielo.orgopendoar:2023-05-16T16:36:44SciELO Preprints - Scientific Electronic Library Online (SCIELO)false |
dc.title.none.fl_str_mv |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS IDEB, LAS UNIDADES FEDERATIVAS Y EL CENSO ESCOLAR: UN ANÁLISIS NO SUPERVISADO IDEB, AS UNIDADES FEDERATIVAS E O CENSO ESCOLAR: UMA ANÁLISE NÃO SUPERVISIONADA |
title |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS |
spellingShingle |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS Alves, Igor Indicadores educacionais ensino fundamental análise exploratória de dados modelos não supervisionados Educational indicators elementary education exploratory data analysis unsupervised models Indicadores educativos educación primaria análisis exploratorio de datos modelos no supervisados |
title_short |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS |
title_full |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS |
title_fullStr |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS |
title_full_unstemmed |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS |
title_sort |
IDEB, THE FEDERATIVE UNITS AND THE SCHOOL CENSUS: AN UNSUPERVISED ANALYSIS |
author |
Alves, Igor |
author_facet |
Alves, Igor Jesus, Rodrigo Romanelli, João Silveira, Carlos |
author_role |
author |
author2 |
Jesus, Rodrigo Romanelli, João Silveira, Carlos |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Alves, Igor Jesus, Rodrigo Romanelli, João Silveira, Carlos |
dc.subject.por.fl_str_mv |
Indicadores educacionais ensino fundamental análise exploratória de dados modelos não supervisionados Educational indicators elementary education exploratory data analysis unsupervised models Indicadores educativos educación primaria análisis exploratorio de datos modelos no supervisados |
topic |
Indicadores educacionais ensino fundamental análise exploratória de dados modelos não supervisionados Educational indicators elementary education exploratory data analysis unsupervised models Indicadores educativos educación primaria análisis exploratorio de datos modelos no supervisados |
description |
This multidisciplinary work proposes new perspectives and reflections on the data from the multifaceted reality of Brazilian education. It was based on a meticulous methodology of unsupervised exploratory analysis, without any expectation of results, in order to allow the emergence of new insights spontaneously from the data. Special attention was given to data visualization in a multidimensional context, as a way to sensorially highlight the most immanent patterns, without compromising statistical rigor. Therefore, the main objective of this research was to create an innovative intertwining of techniques that, in the context of educational data, would offer more opportunities for questions and inquiries than answers. The database consisted of the Basic Education Development Index (Ideb) and the School Census, within a scope limited to elementary education in 58,920 public schools across Brazil. At the heart of the methodology was a Gaussian Copula paired with a recursive Factor Analysis, after careful treatment of missing values, outliers, linear dependencies, and feature selection. As a result, a plurality of patterns was obtained, both known from the literature and unprecedented. Like Ideb having weight in more than one dimension, implying a heterogeneity of associations involving this index, the infrastructure attributes, and the federal units. In conclusion, the methodology has shown to be reliable and robust in the challenge of composing new analytical perspectives on educational data, enabling the expansion of the scope in future studies. |
publishDate |
2024 |
dc.date.none.fl_str_mv |
2024-03-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/preprint info:eu-repo/semantics/publishedVersion |
format |
preprint |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://preprints.scielo.org/index.php/scielo/preprint/view/6097 10.1590/SciELOPreprints.6097 |
url |
https://preprints.scielo.org/index.php/scielo/preprint/view/6097 |
identifier_str_mv |
10.1590/SciELOPreprints.6097 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://preprints.scielo.org/index.php/scielo/article/view/6097/15239 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2023 Carlos Silveira, Igor Alvez, Rodrigo Jesus, João Romanelli https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2023 Carlos Silveira, Igor Alvez, Rodrigo Jesus, João Romanelli https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
SciELO Preprints SciELO Preprints SciELO Preprints |
publisher.none.fl_str_mv |
SciELO Preprints SciELO Preprints SciELO Preprints |
dc.source.none.fl_str_mv |
reponame:SciELO Preprints instname:Scientific Electronic Library Online (SCIELO) instacron:SCI |
instname_str |
Scientific Electronic Library Online (SCIELO) |
instacron_str |
SCI |
institution |
SCI |
reponame_str |
SciELO Preprints |
collection |
SciELO Preprints |
repository.name.fl_str_mv |
SciELO Preprints - Scientific Electronic Library Online (SCIELO) |
repository.mail.fl_str_mv |
scielo.submission@scielo.org |
_version_ |
1797047811733192704 |