Statistics for N = 1: A Non-Parametric Bayesian Approach
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Scientia Medica (Porto Alegre. Online) |
Texto Completo: | https://revistaseletronicas.pucrs.br/scientiamedica/article/view/38066 |
Resumo: | Research in education is often associated with comparing group averages and linear relations in sufficiently large samples and evidence-based practice is about using the outcomes of that research in the practice of education. However, there are questions that are important for the practice of education that cannot really be addressed by comparisons of group averages and linear relations, no matter how large the samples. Besides, different types of constraints including logistic, financial, and ethical ones may make larger-sample research unfeasible or at least questionable. What has remained less known in many fields is that there are study designs and statistical methods for research involving small samples or even individuals that allow us to address questions of importance for the practice of education. This article discusses one type of such situations and provides a simple coherent statistical approach that provides point and interval estimates of differences of interest regardless of the type of the outcome variable and that is of use in other types of studies involving large samples, small samples, and single individuals. |
id |
PUC_RS-25_48377e78c0986f33a66f840ad4d2a3db |
---|---|
oai_identifier_str |
oai:ojs.revistaseletronicas.pucrs.br:article/38066 |
network_acronym_str |
PUC_RS-25 |
network_name_str |
Scientia Medica (Porto Alegre. Online) |
repository_id_str |
|
spelling |
Statistics for N = 1: A Non-Parametric Bayesian ApproachEstatística para N = 1: Uma abordagem Bayesiana não paramétrica95% Credible IntervalPercentage of All Non-Overlapping Data (PAND)Percentage of All Non-Overlapping Data Bayes (PAND-B)Single Case Design (SCD)Single Case Experimental Design (SCED)Intervalo de credibilidade de 95%Porcentagem de todos os dados não sobrepostos (PAND)Porcentagem de todos os Bayes de dados não sobrepostos (PAND-B)Projeto de caixa única (SCD)Projeto Experimental de Caso Único (SCED)Research in education is often associated with comparing group averages and linear relations in sufficiently large samples and evidence-based practice is about using the outcomes of that research in the practice of education. However, there are questions that are important for the practice of education that cannot really be addressed by comparisons of group averages and linear relations, no matter how large the samples. Besides, different types of constraints including logistic, financial, and ethical ones may make larger-sample research unfeasible or at least questionable. What has remained less known in many fields is that there are study designs and statistical methods for research involving small samples or even individuals that allow us to address questions of importance for the practice of education. This article discusses one type of such situations and provides a simple coherent statistical approach that provides point and interval estimates of differences of interest regardless of the type of the outcome variable and that is of use in other types of studies involving large samples, small samples, and single individuals.A pesquisa em educação é frequentemente associada à comparação de médias de grupo e relações lineares em amostras suficientemente grandes, e a prática baseada em evidências trata do uso dos resultados dessa pesquisa na prática educacional. No entanto, há questões importantes para a prática da educação que não podem ser realmente abordadas por comparações de médias de grupo e relações lineares, por maiores que sejam as amostras. Além disso, diferentes tipos de restrições, incluindo as logísticas, financeiras e éticas, podem tornar a pesquisa com amostras maiores inviável ou, pelo menos, questionável. O que tem ficado menos conhecido em muitos campos é que existem desenhos de estudos e métodos estatísticos para pesquisas envolvendo pequenas amostras ou mesmo indivíduos que nos permitem abordar questões de importância para a prática da educação. Este artigo discute um tipo de tais situações e fornece uma abordagem estatística coerente simples que fornece estimativas de ponto e intervalo de diferenças de interesse, independentemente do tipo de variável de resultado e que é útil em outros tipos de estudos envolvendo grandes amostras, pequenas amostras, e indivíduos solteiros.Editora da PUCRS - ediPUCRS2020-12-17info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://revistaseletronicas.pucrs.br/scientiamedica/article/view/3806610.15448/1980-6108.2020.1.38066Scientia Medica; Vol. 30 No. 1 (2020): Single Volume; e38066Scientia Medica; v. 30 n. 1 (2020): Volume Único; e380661980-61081806-556210.15448/1980-6108.2020.1reponame:Scientia Medica (Porto Alegre. Online)instname:Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS)instacron:PUC_RSenghttps://revistaseletronicas.pucrs.br/scientiamedica/article/view/38066/26461Copyright (c) 2020 Scientia Medicahttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessLeppink, Jimmie2021-01-07T13:53:29Zoai:ojs.revistaseletronicas.pucrs.br:article/38066Revistahttps://revistaseletronicas.pucrs.br/scientiamedica/PUBhttps://revistaseletronicas.pucrs.br/scientiamedica/oaiscientiamedica@pucrs.br || editora.periodicos@pucrs.br1980-61081806-5562opendoar:2021-01-07T13:53:29Scientia Medica (Porto Alegre. Online) - Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS)false |
dc.title.none.fl_str_mv |
Statistics for N = 1: A Non-Parametric Bayesian Approach Estatística para N = 1: Uma abordagem Bayesiana não paramétrica |
title |
Statistics for N = 1: A Non-Parametric Bayesian Approach |
spellingShingle |
Statistics for N = 1: A Non-Parametric Bayesian Approach Leppink, Jimmie 95% Credible Interval Percentage of All Non-Overlapping Data (PAND) Percentage of All Non-Overlapping Data Bayes (PAND-B) Single Case Design (SCD) Single Case Experimental Design (SCED) Intervalo de credibilidade de 95% Porcentagem de todos os dados não sobrepostos (PAND) Porcentagem de todos os Bayes de dados não sobrepostos (PAND-B) Projeto de caixa única (SCD) Projeto Experimental de Caso Único (SCED) |
title_short |
Statistics for N = 1: A Non-Parametric Bayesian Approach |
title_full |
Statistics for N = 1: A Non-Parametric Bayesian Approach |
title_fullStr |
Statistics for N = 1: A Non-Parametric Bayesian Approach |
title_full_unstemmed |
Statistics for N = 1: A Non-Parametric Bayesian Approach |
title_sort |
Statistics for N = 1: A Non-Parametric Bayesian Approach |
author |
Leppink, Jimmie |
author_facet |
Leppink, Jimmie |
author_role |
author |
dc.contributor.author.fl_str_mv |
Leppink, Jimmie |
dc.subject.por.fl_str_mv |
95% Credible Interval Percentage of All Non-Overlapping Data (PAND) Percentage of All Non-Overlapping Data Bayes (PAND-B) Single Case Design (SCD) Single Case Experimental Design (SCED) Intervalo de credibilidade de 95% Porcentagem de todos os dados não sobrepostos (PAND) Porcentagem de todos os Bayes de dados não sobrepostos (PAND-B) Projeto de caixa única (SCD) Projeto Experimental de Caso Único (SCED) |
topic |
95% Credible Interval Percentage of All Non-Overlapping Data (PAND) Percentage of All Non-Overlapping Data Bayes (PAND-B) Single Case Design (SCD) Single Case Experimental Design (SCED) Intervalo de credibilidade de 95% Porcentagem de todos os dados não sobrepostos (PAND) Porcentagem de todos os Bayes de dados não sobrepostos (PAND-B) Projeto de caixa única (SCD) Projeto Experimental de Caso Único (SCED) |
description |
Research in education is often associated with comparing group averages and linear relations in sufficiently large samples and evidence-based practice is about using the outcomes of that research in the practice of education. However, there are questions that are important for the practice of education that cannot really be addressed by comparisons of group averages and linear relations, no matter how large the samples. Besides, different types of constraints including logistic, financial, and ethical ones may make larger-sample research unfeasible or at least questionable. What has remained less known in many fields is that there are study designs and statistical methods for research involving small samples or even individuals that allow us to address questions of importance for the practice of education. This article discusses one type of such situations and provides a simple coherent statistical approach that provides point and interval estimates of differences of interest regardless of the type of the outcome variable and that is of use in other types of studies involving large samples, small samples, and single individuals. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-17 |
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://revistaseletronicas.pucrs.br/scientiamedica/article/view/38066 10.15448/1980-6108.2020.1.38066 |
url |
https://revistaseletronicas.pucrs.br/scientiamedica/article/view/38066 |
identifier_str_mv |
10.15448/1980-6108.2020.1.38066 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://revistaseletronicas.pucrs.br/scientiamedica/article/view/38066/26461 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2020 Scientia Medica https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2020 Scientia Medica 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 |
Editora da PUCRS - ediPUCRS |
publisher.none.fl_str_mv |
Editora da PUCRS - ediPUCRS |
dc.source.none.fl_str_mv |
Scientia Medica; Vol. 30 No. 1 (2020): Single Volume; e38066 Scientia Medica; v. 30 n. 1 (2020): Volume Único; e38066 1980-6108 1806-5562 10.15448/1980-6108.2020.1 reponame:Scientia Medica (Porto Alegre. Online) instname:Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS) instacron:PUC_RS |
instname_str |
Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS) |
instacron_str |
PUC_RS |
institution |
PUC_RS |
reponame_str |
Scientia Medica (Porto Alegre. Online) |
collection |
Scientia Medica (Porto Alegre. Online) |
repository.name.fl_str_mv |
Scientia Medica (Porto Alegre. Online) - Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS) |
repository.mail.fl_str_mv |
scientiamedica@pucrs.br || editora.periodicos@pucrs.br |
_version_ |
1809101752122736640 |