Cargando…

What is the value of statistical testing of observational data?

Statistical analysis of medical data aims to reveal patterns that can aid in decision making for future cases and, hopefully, improve patient outcomes. Large and bias‐free datasets, such as those produced in formal randomized clinical trials, are necessary to make such analyses as reliable as possib...

Descripción completa

Detalles Bibliográficos
Autores principales: Jeffery, Nick D., Budke, Christine M., Chanoit, Guillaume P.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley & Sons, Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9795996/
https://www.ncbi.nlm.nih.gov/pubmed/35810406
http://dx.doi.org/10.1111/vsu.13845
_version_ 1784860381931372544
author Jeffery, Nick D.
Budke, Christine M.
Chanoit, Guillaume P.
author_facet Jeffery, Nick D.
Budke, Christine M.
Chanoit, Guillaume P.
author_sort Jeffery, Nick D.
collection PubMed
description Statistical analysis of medical data aims to reveal patterns that can aid in decision making for future cases and, hopefully, improve patient outcomes. Large and bias‐free datasets, such as those produced in formal randomized clinical trials, are necessary to make such analyses as reliable as possible. For a host of reasons, randomized trials are, unfortunately, relatively uncommon in veterinary medicine and surgery, implying that less ideal datasets (mostly observational data) must form the basis for much of our decision making regarding treatment of individual patients under our care. In this review, we first describe the common shortcomings of many observational veterinary datasets when viewed in comparison with their optimal counterparts and highlight how the deficiencies can lead to unreliable conclusions. We illustrate how many of the interpretative problems associated with observational data, predominantly various forms of bias, are not solved, and may even be exacerbated, by statistical analysis. We emphasize the need to examine summary data and its derivation in detail without being lured into relying upon P values to draw conclusions and advocate for completely omitting statistical analysis of many observational datasets. Finally, we present some suggestions for alternative statistical methods, such as propensity scoring and Bayesian methods, which might help reduce the risk of drawing unwarranted, and overconfident, conclusions from imperfect data.
format Online
Article
Text
id pubmed-9795996
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher John Wiley & Sons, Inc.
record_format MEDLINE/PubMed
spelling pubmed-97959962022-12-28 What is the value of statistical testing of observational data? Jeffery, Nick D. Budke, Christine M. Chanoit, Guillaume P. Vet Surg Review Statistical analysis of medical data aims to reveal patterns that can aid in decision making for future cases and, hopefully, improve patient outcomes. Large and bias‐free datasets, such as those produced in formal randomized clinical trials, are necessary to make such analyses as reliable as possible. For a host of reasons, randomized trials are, unfortunately, relatively uncommon in veterinary medicine and surgery, implying that less ideal datasets (mostly observational data) must form the basis for much of our decision making regarding treatment of individual patients under our care. In this review, we first describe the common shortcomings of many observational veterinary datasets when viewed in comparison with their optimal counterparts and highlight how the deficiencies can lead to unreliable conclusions. We illustrate how many of the interpretative problems associated with observational data, predominantly various forms of bias, are not solved, and may even be exacerbated, by statistical analysis. We emphasize the need to examine summary data and its derivation in detail without being lured into relying upon P values to draw conclusions and advocate for completely omitting statistical analysis of many observational datasets. Finally, we present some suggestions for alternative statistical methods, such as propensity scoring and Bayesian methods, which might help reduce the risk of drawing unwarranted, and overconfident, conclusions from imperfect data. John Wiley & Sons, Inc. 2022-07-10 2022-10 /pmc/articles/PMC9795996/ /pubmed/35810406 http://dx.doi.org/10.1111/vsu.13845 Text en © 2022 The Authors. Veterinary Surgery published by Wiley Periodicals LLC on behalf of American College of Veterinary Surgeons. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ (https://creativecommons.org/licenses/by-nc-nd/4.0/) License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.
spellingShingle Review
Jeffery, Nick D.
Budke, Christine M.
Chanoit, Guillaume P.
What is the value of statistical testing of observational data?
title What is the value of statistical testing of observational data?
title_full What is the value of statistical testing of observational data?
title_fullStr What is the value of statistical testing of observational data?
title_full_unstemmed What is the value of statistical testing of observational data?
title_short What is the value of statistical testing of observational data?
title_sort what is the value of statistical testing of observational data?
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9795996/
https://www.ncbi.nlm.nih.gov/pubmed/35810406
http://dx.doi.org/10.1111/vsu.13845
work_keys_str_mv AT jefferynickd whatisthevalueofstatisticaltestingofobservationaldata
AT budkechristinem whatisthevalueofstatisticaltestingofobservationaldata
AT chanoitguillaumep whatisthevalueofstatisticaltestingofobservationaldata