CoChat
Sign Up
Cited by 338Statistical Methods in EpidemiologyStatistical Methods in Clinical TrialsAdvanced Causal Inference Techniques

The DOI matches its Crossref record, with a small difference in title or year; 26 of the 26 references it cites were found in a registry or an index.

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

Open access
Norén, G Niklas, Hopstadius, Johan, Bate, Andrew·2013·Statistical Methods in Medical Research
DOI 10.1177/0962280211403604PMC PMC6331976
Open this paper in CoChat — free accountOpen PDF

Abstract

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1177/0962280211403604

Cites

26 of 26 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1. Schematic overview of an interaction between two conditions A and B relative to an additive baseine model. The bars correspond to the frequency of the event of interest (1) in the absence of both A and B, (2) with A but not B, (3) with B but not A, and (4) with A and B together. The shades correspond to: the marginal relative frequency of the event (lightest), the increased frequency attributable to A, the increased frequency attributable to B, and the increased frequency attributable to an interaction between A and B (darkest).
Figure 1. Schematic overview of an interaction between two conditions A and B relative to an additive baseine model. The bars correspond to the frequency of the event of interest (1) in the absence of both A and B, (2) with A but not B, (3) with B but not A, and (4) with A and B together. The shades correspond to: the marginal relative frequency of the event (lightest), the increased frequency attributable to A, the increased frequency attributable to B, and the increased frequency attributable to an interaction between A and B (darkest).CC BY-NC · PubMed Central
Figure 2. Visualisation of OE ratios over time, for the association in a collection of electronic patient records between first prescriptions of an antihypertensive medicine and diagnoses of swelling. The top panel displays the logarithm of the OE ratio (with shrinkage) over time. The bottom panel displays the underlying observed and expected numbers of events. Reproduced from Norén et al. [9] with permission from Springer.
Figure 2. Visualisation of OE ratios over time, for the association in a collection of electronic patient records between first prescriptions of an antihypertensive medicine and diagnoses of swelling. The top panel displays the logarithm of the OE ratio (with shrinkage) over time. The bottom panel displays the underlying observed and expected numbers of events. Reproduced from Norén et al. [9] with permission from Springer.CC BY-NC · PubMed Central
Figure 3. Visualisation of the retrospective evolution over time of the OE ratio for the association between fluoxetine and neonatal withdrawal syndrome in the WHO Global Individual Case Safety Reports database, VigiBase. The top panel displays the logarithm of the OE ratio (with shrinkage) over time. The bottom panel displays the underlying observed and expected numbers of events.
Figure 3. Visualisation of the retrospective evolution over time of the OE ratio for the association between fluoxetine and neonatal withdrawal syndrome in the WHO Global Individual Case Safety Reports database, VigiBase. The top panel displays the logarithm of the OE ratio (with shrinkage) over time. The bottom panel displays the underlying observed and expected numbers of events.CC BY-NC · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

Sorted by citations

See all 338

Related

See all

Metadata

Authors
Norén, G. N., Hopstadius, J., & Bate, A.
Affiliations
Uppsala Monitoring Centre (SE)
Corresponding author
Norén, G Niklas
ORCID
Venue
Statistical Methods in Medical Research
Publisher
SAGE Publications
Published
2011-06-24
Volume
22
Issue
1
Pages
57-69
ISSN
  • 0962-2802 (ISSN-L)
  • 1477-0334
DOI
10.1177/0962280211403604
PMC
PMC6331976
OpenAlex
W2005366883
Cited by
336
References
26
Citations by year
2026: 45 · 2025: 45 · 2024: 48 · 2023: 46 · 2022: 53 · 2021: 21 · 2020: 17 · 2019: 9 · 2018: 11 · 2017: 5 · 2016: 5 · 2015: 8 · 2014: 10 · 2013: 7 · 2012: 6
FWCI
6.43
Type
journal article
Language
en
Open access
Licence
Locations
  • Statistical Methods in Medical Research (publishedVersion, cc-by-nc)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
  • Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
Keywords
observed-to-expected ratio, pattern discovery, observational data, spurious association, rare events, higher-order interactions, temporal association, associative strength, clinical practice
MeSH terms
Models, Statistical

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review