Statistics applied to plant micropropagation: a critical review of inadequate use
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Bioscience journal (Online) |
Texto Completo: | https://seer.ufu.br/index.php/biosciencejournal/article/view/38778 |
Resumo: | Statistical analyses are an essential part of scientific research. Various procedures since the preparation of the experiment have an impact on the statistical procedures adopted. Therefore, a correct planning implies a precise analysis. Through sampling which used a reliability interval at 95% and error margin at 7%, this study aimed to characterize the statistics used by researchers in the field of plant tissue culture, and based on the results, discuss the main impacts of their misuse. Information regarding sample size; number of repetitions; delineation; scheme adopted (factorial or otherwise) and number of treatments; use (or lack of) data transformation; type of the variable (quantitative or qualitative), test and regression types was quantified. Even with consistent use of statistics in plant tissue culture experiments some hindrances remain, such as the size of the portions and the reduced number of repetitions. Added to this, the transformation of data in which criteria for adoption is not reported or informed, or use of ill-informed criteria. Even considering homogeneous conditions, neglecting to use blocking in experiments may misguide researchers. Blocking is recommended to increase the size of the sample, with time as blocking factor, or the human factor involved in the installation of the experiment. The use of factorial designs has been characteristic of the area, which aims to define doses and plant regulators, so the experiments present large number of treatments. For comparison, Tukey's is used for qualitative data, and for the quantitative, and quadratic linear models are preferred. |
id |
UFU-14_a05817feb399847f27a5f65d597d9327 |
---|---|
oai_identifier_str |
oai:ojs.www.seer.ufu.br:article/38778 |
network_acronym_str |
UFU-14 |
network_name_str |
Bioscience journal (Online) |
repository_id_str |
|
spelling |
Statistics applied to plant micropropagation: a critical review of inadequate use Estatísticas aplicadas a micropropagação de plantas: uma revisão crítica sobre usos inadequadosExperimental designsPlant biotechnologyIn vitro experimental planningAgricultural SciencesStatistical analyses are an essential part of scientific research. Various procedures since the preparation of the experiment have an impact on the statistical procedures adopted. Therefore, a correct planning implies a precise analysis. Through sampling which used a reliability interval at 95% and error margin at 7%, this study aimed to characterize the statistics used by researchers in the field of plant tissue culture, and based on the results, discuss the main impacts of their misuse. Information regarding sample size; number of repetitions; delineation; scheme adopted (factorial or otherwise) and number of treatments; use (or lack of) data transformation; type of the variable (quantitative or qualitative), test and regression types was quantified. Even with consistent use of statistics in plant tissue culture experiments some hindrances remain, such as the size of the portions and the reduced number of repetitions. Added to this, the transformation of data in which criteria for adoption is not reported or informed, or use of ill-informed criteria. Even considering homogeneous conditions, neglecting to use blocking in experiments may misguide researchers. Blocking is recommended to increase the size of the sample, with time as blocking factor, or the human factor involved in the installation of the experiment. The use of factorial designs has been characteristic of the area, which aims to define doses and plant regulators, so the experiments present large number of treatments. For comparison, Tukey's is used for qualitative data, and for the quantitative, and quadratic linear models are preferred.As análises estatísticas são uma parte essencial da pesquisa científica. Vários procedimentos desde a elaboração do experimento têm impacto nos procedimentos estatísticos finais adotados, assim um correto planejamento implica em uma análise precisa. Por meio de uma amostragem utilizando intervalo de confiança a 95% e margem de erro de 7% objetivou caracterizar as estatísticas utilizadas pelos pesquisadores da área de cultura de tecidos vegetais, e com base nos resultados discutir os principais impactos do mau uso. Foram quantificadas as informações referentes ao tamanho da amostra; número de repetições; delineamento; esquema adotado (fatorial ou não) e número de tratamentos; uso ou não de transformação, critério para adoção e tipo de transformação; tipo da variável (quantitativo ou qualitativo), teste e tipos de regressão. Mesmo com uso consistente da estatística nos experimentos de micropropagação alguns argalospermanecem, como o tamanho das parcelas e o número reduzido de repetições. Soma-se a isto, a transformação de dados na qual não são informados os critérios para a adoção, ou usam-se critérios equivocados. Mesmo considerando as condições homogêneas, o não uso da blocagem nos experimentos pode configurar em um erro. Recomenda-se a blocagem para aumentar o tamanho da amostra, tendo como bloco o tempo e, ou, o fator humano envolvido na instalação do experimento. Como característica da área tem-se o uso de experimentos fatoriais, visando definir doses e reguladores vegetais, assim os experimentos apresentam grande número de tratamentos. Para comparação dos dados qualitativos utiliza-se o teste de Tukey e no quantitativo as regressões preferidas são as lineares e quadráticas.EDUFU2018-10-11info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://seer.ufu.br/index.php/biosciencejournal/article/view/3877810.14393/BJ-v34n5a2018-38778Bioscience Journal ; Vol. 34 No. 5 (2018): Sept./Oct.; 1308-1318Bioscience Journal ; v. 34 n. 5 (2018): Sept./Oct.; 1308-13181981-3163reponame:Bioscience journal (Online)instname:Universidade Federal de Uberlândia (UFU)instacron:UFUenghttps://seer.ufu.br/index.php/biosciencejournal/article/view/38778/24226Brazil; ContemporaryCopyright (c) 2018 Vanderley José Pereira, Simone Abreu Asmar, Nádia Giaretta Biase, José Magno Queiroz Luz, Berildo de Melohttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessPereira, Vanderley JoséAsmar, Simone AbreuBiase, Nádia GiarettaLuz, José Magno QueirozMelo, Berildo de2022-02-10T13:00:47Zoai:ojs.www.seer.ufu.br:article/38778Revistahttps://seer.ufu.br/index.php/biosciencejournalPUBhttps://seer.ufu.br/index.php/biosciencejournal/oaibiosciencej@ufu.br||1981-31631516-3725opendoar:2022-02-10T13:00:47Bioscience journal (Online) - Universidade Federal de Uberlândia (UFU)false |
dc.title.none.fl_str_mv |
Statistics applied to plant micropropagation: a critical review of inadequate use Estatísticas aplicadas a micropropagação de plantas: uma revisão crítica sobre usos inadequados |
title |
Statistics applied to plant micropropagation: a critical review of inadequate use |
spellingShingle |
Statistics applied to plant micropropagation: a critical review of inadequate use Pereira, Vanderley José Experimental designs Plant biotechnology In vitro experimental planning Agricultural Sciences |
title_short |
Statistics applied to plant micropropagation: a critical review of inadequate use |
title_full |
Statistics applied to plant micropropagation: a critical review of inadequate use |
title_fullStr |
Statistics applied to plant micropropagation: a critical review of inadequate use |
title_full_unstemmed |
Statistics applied to plant micropropagation: a critical review of inadequate use |
title_sort |
Statistics applied to plant micropropagation: a critical review of inadequate use |
author |
Pereira, Vanderley José |
author_facet |
Pereira, Vanderley José Asmar, Simone Abreu Biase, Nádia Giaretta Luz, José Magno Queiroz Melo, Berildo de |
author_role |
author |
author2 |
Asmar, Simone Abreu Biase, Nádia Giaretta Luz, José Magno Queiroz Melo, Berildo de |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Pereira, Vanderley José Asmar, Simone Abreu Biase, Nádia Giaretta Luz, José Magno Queiroz Melo, Berildo de |
dc.subject.por.fl_str_mv |
Experimental designs Plant biotechnology In vitro experimental planning Agricultural Sciences |
topic |
Experimental designs Plant biotechnology In vitro experimental planning Agricultural Sciences |
description |
Statistical analyses are an essential part of scientific research. Various procedures since the preparation of the experiment have an impact on the statistical procedures adopted. Therefore, a correct planning implies a precise analysis. Through sampling which used a reliability interval at 95% and error margin at 7%, this study aimed to characterize the statistics used by researchers in the field of plant tissue culture, and based on the results, discuss the main impacts of their misuse. Information regarding sample size; number of repetitions; delineation; scheme adopted (factorial or otherwise) and number of treatments; use (or lack of) data transformation; type of the variable (quantitative or qualitative), test and regression types was quantified. Even with consistent use of statistics in plant tissue culture experiments some hindrances remain, such as the size of the portions and the reduced number of repetitions. Added to this, the transformation of data in which criteria for adoption is not reported or informed, or use of ill-informed criteria. Even considering homogeneous conditions, neglecting to use blocking in experiments may misguide researchers. Blocking is recommended to increase the size of the sample, with time as blocking factor, or the human factor involved in the installation of the experiment. The use of factorial designs has been characteristic of the area, which aims to define doses and plant regulators, so the experiments present large number of treatments. For comparison, Tukey's is used for qualitative data, and for the quantitative, and quadratic linear models are preferred. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-10-11 |
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.ufu.br/index.php/biosciencejournal/article/view/38778 10.14393/BJ-v34n5a2018-38778 |
url |
https://seer.ufu.br/index.php/biosciencejournal/article/view/38778 |
identifier_str_mv |
10.14393/BJ-v34n5a2018-38778 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://seer.ufu.br/index.php/biosciencejournal/article/view/38778/24226 |
dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.coverage.none.fl_str_mv |
Brazil; Contemporary |
dc.publisher.none.fl_str_mv |
EDUFU |
publisher.none.fl_str_mv |
EDUFU |
dc.source.none.fl_str_mv |
Bioscience Journal ; Vol. 34 No. 5 (2018): Sept./Oct.; 1308-1318 Bioscience Journal ; v. 34 n. 5 (2018): Sept./Oct.; 1308-1318 1981-3163 reponame:Bioscience journal (Online) instname:Universidade Federal de Uberlândia (UFU) instacron:UFU |
instname_str |
Universidade Federal de Uberlândia (UFU) |
instacron_str |
UFU |
institution |
UFU |
reponame_str |
Bioscience journal (Online) |
collection |
Bioscience journal (Online) |
repository.name.fl_str_mv |
Bioscience journal (Online) - Universidade Federal de Uberlândia (UFU) |
repository.mail.fl_str_mv |
biosciencej@ufu.br|| |
_version_ |
1797069078317236224 |