Methodology

Every statistic on this site is derived from public data published by national statistical agencies. This page lists every source and explains every estimation step.

Primary sources

• Office for National Statistics - Baby Names
  License: Open Government Licence v3.0 - Coverage: 1996/ - Region: England and Wales
• U.S. Social Security Administration - National Names Data
  License: U.S. Public Domain - Coverage: 1880/ - Region: United States
• U.S. Social Security Administration - State Names Data
  License: U.S. Public Domain - Coverage: 1910/ - Region: United States (50 states + DC)
• U.S. Census Bureau - 2010 Frequently Occurring Surnames
  License: U.S. Public Domain - Coverage: 2010 - Region: United States
• Wikidata - Famous Bearers
  License: CC0 1.0 - Coverage: ongoing - Region: Worldwide

Living-bearer estimate

SSA data gives births per year. To estimate the living population, we apply age-specific survival probabilities from the SSA Period Life Table to each birth year, then sum. The implementation is in lib/utils/survival.ts.

Worldwide estimate

Where we have a primary source for a country we sum directly. Where we do not, we estimate prevalence using a reference country and apply that to the destination country's population. Estimated values are clearly flagged with "est." on each name page.

Combined-name estimate

For full-name combinations (first + last) we use the independence assumption: prevalence(first) x prevalence(last) x population. This produces an order-of-magnitude estimate only.

Refresh cadence

SSA publishes annually around May. We refresh within 30 days of release. ONS UK publishes annually in autumn. Other agencies vary - see the dates next to each dataset above.