B Evidence Grade B Graded accuracy verified by the review judge Safe to Cite Recent

3%

3% -- false winner rate for Bayesian A/B tests using flat priors after one week (2025)

2025  · Andrew Gelman

More than 3% of Bayesian A/B tests using flat priors select fake winners after one week.

  • Attributed as a warning/simulation result by Andrew Gelman regarding flat priors
Cite this stat Share How we verify
Attribution: Andrew Gelman View source
Lighthouse Research Team
Last verified:  ·  How we verify data →
Source verified Evidence graded
Value
3%
Unit
Percentage
Data Vintage
2025
Entity
Bayesian A/B tests using flat priors after one week
B
Strong, reliable evidence

Sourced from a well-regarded research firm or industry leader with transparent methodology and a reasonably large sample.

61/100 confidence

Single source - not yet corroborated

Extraction
50
Source Trust
60
Citation Chain
20
Independence
30
Methodology
45
Freshness
95
Andrew Gelman Primary Tier C
https://kirro.io/bayesian-ab-testing ↗
Confidence: 48/100 Vintage: 2025 Channel: Deep Crawl
Source Article
Bayesian A/B Testing: When It Helps, When It Is Overkill
Bayesian A/B testing measures which version of a page works better using a probability that updates as data comes in. Instead of waiting for some magic number of visitors, you get a running answer: “Version B has an 89% chance of getting more signups.” That’s it. No statistics degree required. Peopl…
Original Research
Andrew Gelman · Original study ↗

Attributed to Andrew Gelman's warning on flat priors, cited by Kirro

Methodology documented
Industrymarketing
Plain Text
Bayesian A/B tests using flat priors after one week: 3% false winner rate. Source: Andrew Gelman (2025). Via Lighthouse Intelligence -- https://lighthousedata.io/data/flat-prior-fake-winners-3
HTML Embed
<blockquote cite="https://lighthousedata.io/data/flat-prior-fake-winners-3" style="border-left:3px solid #2563eb;padding:12px 16px;margin:16px 0;font-family:system-ui,sans-serif;background:#f0f4ff;"><strong>3%</strong> -- false winner rate for Bayesian A/B tests using flat priors after one week<br><small>Source: Andrew Gelman (2025) · <a href="https://lighthousedata.io/data/flat-prior-fake-winners-3" target="_blank" rel="noopener">Lighthouse Intelligence</a></small></blockquote>
Share
Share on X Share on LinkedIn

Use this data in your work

Copy the citation, embed the widget, or explore thousands more verified marketing statistics -- all free.

Copy citation Explore similar stats →