# Geo Lift Test

> A test that runs ads in some towns but not others. Then it compares sales.

**Field:** Marketing & SEO  
**Category:** Attribution & Testing  
**Also known as:** Geo Experiment, Matched Market Test, Geo Test

## Think of it like

It is like trying a new menu in some towns but not others. Then you compare the towns.

## Definition

A geo lift test measures a campaign by running it in some places and not in others. The places are picked to be alike, such as cities with similar sales. After the test, you compare sales in the two sets of places. The extra sales where the ads ran are the lift. It works even when you cannot track single people.

## Example

A coffee chain runs TV ads in Manchester and Leeds but not in two matched cities. Sales rise 6% more where the ads ran, and that is the lift.

## Why it matters

It needs no cookies and does not track people. So privacy rules do not get in the way.

## Common mistake

Comparing places that were never alike. A city with a big event that month will skew the answer.

## Three principles

- **Places, not people.** Regions are the test groups.
- **Matched pairs.** Pick markets that look alike.
- **Works offline too.** TV and posters can be tested.

## Related terms

- [Incrementality](https://learn.benibix.com/term/marketing/incrementality)
- [Holdout Group](https://learn.benibix.com/term/marketing/holdout-group)
- [Marketing Mix Modeling (MMM)](https://learn.benibix.com/term/marketing/marketing-mix-modeling)
- [Conversion Lift Study](https://learn.benibix.com/term/marketing/conversion-lift-study)
- [Measurement Triangulation](https://learn.benibix.com/term/marketing/measurement-triangulation)

## Told apart from

- [Conversion Lift Study vs Geo Lift Test](https://learn.benibix.com/compare/conversion-lift-study-vs-geo-lift-test): People think a lift test is a lift test, and these two split different things. A conversion lift study splits people at random inside one ad platform. A geo lift test splits places, like cities, and holds the ads back in some of them. The first is run by the platform and tests only its ads. The second can test any channel, even TV, but it needs more money and time.

![Two bars side by side. The group that saw the ads reached 1,200 sales and the held-out group reached 1,000. The top 200 of the first bar is shaded and labelled lift.](https://learn.benibix.com/diagrams/incrementality.svg)

---

Source: https://learn.benibix.com/term/marketing/geo-lift-test
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-20
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
