What does census-grounded mean?

Each simulated respondent is built from census-style demographic margins (age, education, income, race, party, place), not from a random draw of living people. The answers are generated by a model. The published check is how close the aggregate comes to real polls.

When is a synthetic screen the right tool?

When you need to drop a weak message, catch a leading question, or take a first read across markets before you spend on humans. A traditional focus group often costs $4,000 to $12,000 and takes weeks to recruit.

When do I still need a human sample?

When the sample itself is the deliverable: litigation, a regulatory filing, a published journalism poll, or any number that has to be defended as a probability design. Every Lewsearch report states the answers are AI-generated.

Answers

Is synthetic research a probability sample?

Last updated: August 25, 2026

Synthetic research is not a probability sample. Lewsearch interviews census-grounded living agents and publishes 7.47% mean absolute error on 404 ex-electoral questions of a 460-question public-poll benchmark. Use it to screen messages and instruments. Hire humans when the number has to stand up in court, at a regulator, or in a newspaper.

What a probability sample is

A probability sample starts with a defined frame of real people. Every unit in that frame has a known, non-zero chance of selection. The statistician can write the design, the weights, and the sampling error. A court, a regulator, or a newspaper can ask who was eligible, who was reached, and how non-response was handled. The number stands or falls on that design.

That is a human research product. It takes time and money because the people have to be found.

Why a synthetic panel is not one

A Lewsearch study does not draw people from a frame. It draws simulated respondents whose demographics match a market's published margins, interviews them with a model, and tabulates the answers. There is no inclusion probability. There is no non-response. There is no person who could have been selected and was not. The output looks like a survey (option shares, crosstabs, quotes, a PDF). The design is not a survey sample.

The published check is the miss against real polls, not a sampling margin. 7.47% mean absolute error on 404 ex-electoral questions of a 460-question benchmark vs real polls (Pew, Gallup, UT/Texas Politics Project, PPIC). Mean absolute error is the average miss in percentage points. It is not a plus-minus interval around this study. Do not write it with a plus-minus sign, and do not say "7.47% across 460 questions." The 7.47% is the 404-question ex-electoral slice of a 460-question pool.

Probability sample versus a synthetic panel
	Probability sample	Lewsearch synthetic panel
Who answers	Recruited people from a defined frame	Census-grounded simulated respondents
What you can defend	The design, if it holds	An AI-labeled directional read
Error you can quote	Sampling error from the design	7.47% MAE on scored public-poll items
Where it can be filed	Court, regulator, newspaper, if the design holds	A screen, not a legal sample

What census-grounded means here

Census-grounded means the demographic row is built from census-style margins, not that a Census Bureau interview took place. Age, education, income, race, party, and place are drawn so a 500-person Ohio study is 500 distinct rows, not 500 copies of "an Ohioan." The published pool is over 650,000 simulated respondents. A study samples a market. It does not interview the whole pool. Live coverage is on coverage (27 live panels · U.S. national · 4 census regions (32 audiences)).

The answers still come from a model. Every report says so on the cover. Accuracy is scored by comparing the aggregate to published polls on methodology.

When a screen is the right tool

Use the synthetic pass to drop a confused option, lint a leading or double-barreled item, rank messages before media spend, or take a first read across markets. A team can run several framings for the price of one facility group. Queued studies return in about 15 minutes. Prices live on pricing.

A low MAE on a category you did not ask is not a warranty. A high MAE on a category you did ask is a reason to hire humans or rewrite the question. The per-question file is public.

When the number has to be human

Hire a probability sample when the result has to stand up in court, at a regulator, or in a newspaper. The same rule covers clinical or highly specialized populations you cannot score, demand forecasts you will take to a board as fact, and any filing that treats the sample itself as the deliverable. Lewsearch's own terms say the same thing: results are directional research, not a substitute for probabilistic sampling in those contexts.

The product is a screen.

FAQ

Is synthetic research a probability sample?: Synthetic research is not a probability sample. Lewsearch interviews census-grounded living agents and publishes 7.47% mean absolute error on 404 ex-electoral questions of a 460-question public-poll benchmark. Use it to screen messages and instruments. Hire humans when the number has to stand up in court, at a regulator, or in a newspaper.
What does census-grounded mean?: Each simulated respondent is built from census-style demographic margins (age, education, income, race, party, place), not from a random draw of living people. The answers are generated by a model. The published check is how close the aggregate comes to real polls.
When is a synthetic screen the right tool?: When you need to drop a weak message, catch a leading question, or take a first read across markets before you spend on humans. A traditional focus group often costs $4,000 to $12,000 and takes weeks to recruit.
When do I still need a human sample?: When the sample itself is the deliverable: litigation, a regulatory filing, a published journalism poll, or any number that has to be defended as a probability design. Every Lewsearch report states the answers are AI-generated.

Check the work

Methodology and coverage Pricing Compare vendors Run a study