What not to do in medical statistics

Detalhes bibliográficos
Autor(a) principal: Alexander,Neal
Data de Publicação: 2007
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Revista Brasileira de Saúde Materno Infantil (Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1519-38292007000300012
Resumo: There have been major efforts to improve the application of statistical methods in medical research, although some errors and misconceptions persist. In this paper I will review some of the topics which most often cause problems: a) comparison of two methods of clinical measurement; b) comparison of baseline values between arms of a randomized trial; c) absence of evidence as opposed to evidence of absence; and d) regression to the mean. I will also revisit a statistical error in one of my own publications. I review some causes of the continuing misuse of statistics, and make some suggestions for modifying the education of statistical and non-statistical medical researchers in order to alleviate this.
id IMIPFF-1_d1ae3b0fe34dc71c0a5a11451d8cc161
oai_identifier_str oai:scielo:S1519-38292007000300012
network_acronym_str IMIPFF-1
network_name_str Revista Brasileira de Saúde Materno Infantil (Online)
repository_id_str
spelling What not to do in medical statisticsStatisticsBiostatisticsThere have been major efforts to improve the application of statistical methods in medical research, although some errors and misconceptions persist. In this paper I will review some of the topics which most often cause problems: a) comparison of two methods of clinical measurement; b) comparison of baseline values between arms of a randomized trial; c) absence of evidence as opposed to evidence of absence; and d) regression to the mean. I will also revisit a statistical error in one of my own publications. I review some causes of the continuing misuse of statistics, and make some suggestions for modifying the education of statistical and non-statistical medical researchers in order to alleviate this.Instituto de Medicina Integral Prof. Fernando Figueira2007-09-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1519-38292007000300012Revista Brasileira de Saúde Materno Infantil v.7 n.3 2007reponame:Revista Brasileira de Saúde Materno Infantil (Online)instname:Instituto de Medicina Integral Prof. Fernando Figueira (IMIPFF)instacron:IMIPFF10.1590/S1519-38292007000300012info:eu-repo/semantics/openAccessAlexander,Nealeng2007-10-05T00:00:00Zoai:scielo:S1519-38292007000300012Revistahttp://www.scielo.br/rbsmihttps://old.scielo.br/oai/scielo-oai.php||revista@imip.org.br1806-93041519-3829opendoar:2007-10-05T00:00Revista Brasileira de Saúde Materno Infantil (Online) - Instituto de Medicina Integral Prof. Fernando Figueira (IMIPFF)false
dc.title.none.fl_str_mv What not to do in medical statistics
title What not to do in medical statistics
spellingShingle What not to do in medical statistics
Alexander,Neal
Statistics
Biostatistics
title_short What not to do in medical statistics
title_full What not to do in medical statistics
title_fullStr What not to do in medical statistics
title_full_unstemmed What not to do in medical statistics
title_sort What not to do in medical statistics
author Alexander,Neal
author_facet Alexander,Neal
author_role author
dc.contributor.author.fl_str_mv Alexander,Neal
dc.subject.por.fl_str_mv Statistics
Biostatistics
topic Statistics
Biostatistics
description There have been major efforts to improve the application of statistical methods in medical research, although some errors and misconceptions persist. In this paper I will review some of the topics which most often cause problems: a) comparison of two methods of clinical measurement; b) comparison of baseline values between arms of a randomized trial; c) absence of evidence as opposed to evidence of absence; and d) regression to the mean. I will also revisit a statistical error in one of my own publications. I review some causes of the continuing misuse of statistics, and make some suggestions for modifying the education of statistical and non-statistical medical researchers in order to alleviate this.
publishDate 2007
dc.date.none.fl_str_mv 2007-09-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1519-38292007000300012
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1519-38292007000300012
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/S1519-38292007000300012
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Instituto de Medicina Integral Prof. Fernando Figueira
publisher.none.fl_str_mv Instituto de Medicina Integral Prof. Fernando Figueira
dc.source.none.fl_str_mv Revista Brasileira de Saúde Materno Infantil v.7 n.3 2007
reponame:Revista Brasileira de Saúde Materno Infantil (Online)
instname:Instituto de Medicina Integral Prof. Fernando Figueira (IMIPFF)
instacron:IMIPFF
instname_str Instituto de Medicina Integral Prof. Fernando Figueira (IMIPFF)
instacron_str IMIPFF
institution IMIPFF
reponame_str Revista Brasileira de Saúde Materno Infantil (Online)
collection Revista Brasileira de Saúde Materno Infantil (Online)
repository.name.fl_str_mv Revista Brasileira de Saúde Materno Infantil (Online) - Instituto de Medicina Integral Prof. Fernando Figueira (IMIPFF)
repository.mail.fl_str_mv ||revista@imip.org.br
_version_ 1752129927756382208

Registros relacionados