Confounding and Simpson's paradox
Open accessAbstract
Details ofreconstructive surgery and amputations carried out in districts with below (low volume) and above (high volume) the average rate of arterial reconstructions in the Oxford region.Values are numbers or proportions (percentages) Statistics High volume Low volume x2 df P value Referrals from outside the district 10/67 (15) 2/46 (4 3) 2-197 1 0-138 Balloon angioplasty before reconstructive surgery 23/67 (34) 3/41 (7-3) 8-729 1 0-0031 Types of infrainguinal graft: Femorotibial graft 17 (25) 4 (11) Femoropopliteal: 1 23-943 2 00001 Vein 31 (46) 4 (11) 293 2 000 Prosthesis 19 (28) 27 ( 77) Amputation rate per 100 000 population peryear (95% confidence interval) 6-1 (40 to 8 2) 10-3 (7-4to 13-2) 5-365 1 0-021 Ratio ofbelow knee to above knee amputations
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Simpson's paradox is problematic for causal hypotheses that should hold both within and between clusters, such as the notion that gender equality causes a manifest divergence of men and women.
“This is problematic for causal hypotheses that should hold both within and between clusters, such as the notion that gender equality causes a manifest divergence of men and women.”
From Simpson’s gender-equality paradox (2025) · cites this paper as [31]
Cites
The interpretation of interaction in contingency tables
Simpson, E. H. (1951) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1951.tb00088.x · Cited by 2,301 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Simpson's paradox in psychological science: a practical guide
Kievit, R. A., Frankenhuis, W. E., Waldorp, L. J., & Borsboom, D. (2013) · Frontiers in Psychology · doi:10.3389/fpsyg.2013.00513 · Cited by 542 · see citing works
O'Reilly-Shah, V. N., Gentry, K. R., Walters, A. M., Zivot, J., Anderson, C. T., & Tighe, P. J. (2020) · British Journal of Anaesthesia · doi:10.1016/j.bja.2020.07.040 · Cited by 62 · see citing works
Chuang‐Stein, C., & Beltangady, M. (2011) · Pharmaceutical Statistics · doi:10.1002/pst.397 · Cited by 43 · see citing works
Simpson’s gender-equality paradox
Berggren, M., & Bergh, R. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2422247122 · Cited by 17 · see citing works
- Authors
- Julious, S. A., & Mullee, M. A.
- Affiliations
- Southampton General Hospital (GB)
- ORCID
- Julious, Steven A
- Venue
- BMJ
- Publisher
- BMJ
- Published
- 1994-12-03
- Volume
- 309
- Issue
- 6967
- Pages
- 1480-1481
- ISSN
- 0007-1447 (ISSN-L)
- 0959-8138
- 1468-5833
- PMC
- PMC2541623
- OpenAlex
- W1995865988
- Cited by
- 179
- References
- 1
- Citations by year
- 2026: 10 · 2025: 8 · 2024: 5 · 2023: 12 · 2022: 11 · 2021: 14 · 2020: 12 · 2019: 6 · 2018: 11 · 2017: 6 · 2016: 3 · 2015: 9 · 2014: 8 · 2013: 6 · 2012: 8
- FWCI
- 1.74
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- www.bmj.com/company/legal-information/terms-conditions/legal-information/tdm-licencepolicy (tdm)
- Locations
- BMJ (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Surgery › Peripheral Artery Disease Management
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Keywords
- arterial reconstruction, amputation rate, transtibial amputation, balloon angioplasty, femoropopliteal graft, vein grafts, prosthetic graft, surgical volume, confounding, Simpson's paradox, Oxford region
- MeSH terms
- Data Interpretation, Statistical, Humans, Models, Statistical, Confounding Factors, Epidemiologic
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
