census.world

Methodology

A population you can check, then ask

How the synthetic population is built from public statistics, how every build is validated, what an answer contains, and which known methods all of it stands on.

How it works

1 · Skeleton

The Census Bureau's 2025 population estimates give every state's population by single year of age, sex, race and Hispanic origin. That joint is reproduced exactly.

2 · Calibration

American Community Survey microdata is raked to that skeleton and to published tables, so education, work, income, family, citizenship, disability, insurance, commute and housing carry the survey's real joint structure. Health and behaviour come from the NHIS by demographic cell.

3 · Validation

Every build holds out published tables it never fitted and reports the error, per state. A number is only claimed with its held-out score.

4 · Asking

A representative sample of profiles answers the question, ten at a time, each as itself. The interval narrows as the sample grows; the reasons people give are collected across the answers.

No real person in the dataPublic sources onlyContent-free idsReproducible, versioned buildsEvery number with its interval

What an answer contains

Not one model’s opinion. A representative sample of synthetic people, each answering as themselves, with everything needed to judge the result.

The answer, with its interval

The share choosing each option, or the mean, with a 95% interval that narrows as more profiles are asked.

The estimate as it forms

The running estimate batch by batch, so you watch it settle rather than trust a single number.

Why they answered

A handful of the people asked explain their answer in their own words, across the answers, with a short reading of what drives the split.

Who said what

The answer by sex, age, education, employment and state, from the sample's own attributes, with the biggest gaps called out.

The people asked

Synthetic profiles and their individual answers. Tangible, and never a real person.

How it was computed

Exactly how the question was put to each person, the population it was asked of, the accuracy record for that kind of question, and the assumptions made along the way.

Validation comes first

A number is only worth what its check is worth. Every kind of question carries its own accuracy record, checked against real surveys, and every answer says which. Every check, with its number.

Matched to the census

Every state's population by single year of age, sex, race and origin is reproduced within sampling error. Not approximately: cell by cell.

Checked on tables it never saw

Published tables are held out of the calibration and predicted afterwards. Employment by sex and age across all states: median error 2.8%. Marital status, veterans, disability, insurance, citizenship, occupation, industry, commute and enrollment are checked the same way.

Compared with real people

On 63 attitude and self-report questions from the General Social Survey, simulated answers sit a median 0.23 total-variation distance from real answers within sex, age and education groups: 0.17 on yes-or-no questions, 0.24 on choices, 0.27 on scales and 0.30 on amounts, where the model still gives rounder numbers than people do. The misses are reported with the hits.

Where a kind of question has not been checked against a real survey yet, the answer page says so in the same sentence that gives the interval.

Three ways to get an answer

Recruit a panel, prompt a model, or ask a calibrated population. They differ in what the answer is grounded in.

A survey panelPersonas from a promptcensus.world
Who answersRecruited respondents, weighted afterwardsCharacters a model invents from a descriptionOne synthetic profile per resident, built from census and survey records
Representative ofThe panel, after weightingWhatever the prompt impliesThe population, cell by cell: state, age, sex, race, origin, education, work, income, household, health
Sampling intervalYesNoYes, on every number, narrowing as more profiles are asked
Checked againstItselfUsually a handful of past surveysOfficial tables held out of the build, and real survey answers by demographic group
ReproducibleNo: a new field, a new sampleNo: a new prompt, a new crowdYes: versioned builds, the same person in every build of a lineage
TimeWeeksMinutesMinutes, with the interval shown as it forms
CostPer respondentPer callThe first hundred profiles of every question are free; full runs by arrangement

Standing on known methods

Nothing here is a new idea. The population is built with methods statisticians have used for decades, applied end to end and checked at every step.

  1. 1940
    Iterative proportional fitting
    Deming and Stephan's method for adjusting a table to known margins; the basis of raking in survey weighting ever since.
    In census.world today
    American Community Survey records are raked to every state's census cell counts and to published tables, so each state's education, work and income structure matches what the Census Bureau reports.
  2. 1996
    Synthetic populations for microsimulation
    Beckman, Baggerly and McKay's synthetic baseline populations for transport models: survey records expanded to a whole population that matches census constraints.
    In census.world today
    One synthetic profile per resident, at any scale up to one-to-one, carrying the survey's joint structure rather than independently drawn attributes.
  3. 2009
    Held-out validation of synthetic populations
    The practice, common since the population-synthesis literature of the 2000s, of scoring a synthetic population on tables it was not fitted to.
    In census.world today
    Every build predicts employment, marital status, veteran status, disability, insurance, citizenship, occupation, industry, commute and enrollment tables it never saw, and reports the error per state.
  4. 2023
    Language models as simulated respondents
    Argyle and colleagues' finding that a language model conditioned on a real respondent's demographics reproduces survey response patterns, and the wave of work testing where that holds and where it fails.
    In census.world today
    Each profile answers in character from its own record; the answers are checked against the General Social Survey by demographic group, and the page says how far off that kind of question tends to be.