Cargando…

Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery

Large observational data sets are a great asset to better understand the effects of medicines in clinical practice and, ultimately, improve patient care. For an empirical pattern in observational data to be of practical relevance, it should represent a substantial deviation from the null model. For...

Descripción completa

Detalles Bibliográficos
Autores principales: Norén, G Niklas, Hopstadius, Johan, Bate, Andrew
Formato: Online Artículo Texto
Lenguaje:English
Publicado: SAGE Publications 2011
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6331976/
https://www.ncbi.nlm.nih.gov/pubmed/21705438
http://dx.doi.org/10.1177/0962280211403604
_version_ 1783387241576398848
author Norén, G Niklas
Hopstadius, Johan
Bate, Andrew
author_facet Norén, G Niklas
Hopstadius, Johan
Bate, Andrew
author_sort Norén, G Niklas
collection PubMed
description Large observational data sets are a great asset to better understand the effects of medicines in clinical practice and, ultimately, improve patient care. For an empirical pattern in observational data to be of practical relevance, it should represent a substantial deviation from the null model. For the purpose of identifying such deviations, statistical significance tests are inadequate, as they do not on their own distinguish the magnitude of an effect from its data support. The observed-to-expected (OE) ratio on the other hand directly measures strength of association and is an intuitive basis to identify a range of patterns related to event rates, including pairwise associations, higher order interactions and temporal associations between events over time. It is sensitive to random fluctuations for rare events with low expected counts but statistical shrinkage can protect against spurious associations. Shrinkage OE ratios provide a simple but powerful framework for large-scale pattern discovery. In this article, we outline a range of patterns that are naturally viewed in terms of OE ratios and propose a straightforward and effective statistical shrinkage transformation that can be applied to any such ratio. The proposed approach retains emphasis on the practical relevance and transparency of highlighted patterns, while protecting against spurious associations.
format Online
Article
Text
id pubmed-6331976
institution National Center for Biotechnology Information
language English
publishDate 2011
publisher SAGE Publications
record_format MEDLINE/PubMed
spelling pubmed-63319762019-01-29 Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery Norén, G Niklas Hopstadius, Johan Bate, Andrew Stat Methods Med Res Articles Large observational data sets are a great asset to better understand the effects of medicines in clinical practice and, ultimately, improve patient care. For an empirical pattern in observational data to be of practical relevance, it should represent a substantial deviation from the null model. For the purpose of identifying such deviations, statistical significance tests are inadequate, as they do not on their own distinguish the magnitude of an effect from its data support. The observed-to-expected (OE) ratio on the other hand directly measures strength of association and is an intuitive basis to identify a range of patterns related to event rates, including pairwise associations, higher order interactions and temporal associations between events over time. It is sensitive to random fluctuations for rare events with low expected counts but statistical shrinkage can protect against spurious associations. Shrinkage OE ratios provide a simple but powerful framework for large-scale pattern discovery. In this article, we outline a range of patterns that are naturally viewed in terms of OE ratios and propose a straightforward and effective statistical shrinkage transformation that can be applied to any such ratio. The proposed approach retains emphasis on the practical relevance and transparency of highlighted patterns, while protecting against spurious associations. SAGE Publications 2011-06-24 2013-02 /pmc/articles/PMC6331976/ /pubmed/21705438 http://dx.doi.org/10.1177/0962280211403604 Text en © The Author(s) 2011 http://creativecommons.org/licenses/by-nc/4.0/ This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (http://www.creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).
spellingShingle Articles
Norén, G Niklas
Hopstadius, Johan
Bate, Andrew
Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery
title Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery
title_full Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery
title_fullStr Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery
title_full_unstemmed Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery
title_short Shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery
title_sort shrinkage observed-to-expected ratios for robust and transparent large-scale pattern discovery
topic Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6331976/
https://www.ncbi.nlm.nih.gov/pubmed/21705438
http://dx.doi.org/10.1177/0962280211403604
work_keys_str_mv AT norengniklas shrinkageobservedtoexpectedratiosforrobustandtransparentlargescalepatterndiscovery
AT hopstadiusjohan shrinkageobservedtoexpectedratiosforrobustandtransparentlargescalepatterndiscovery
AT bateandrew shrinkageobservedtoexpectedratiosforrobustandtransparentlargescalepatterndiscovery