# Holdout group

A comparison group deliberately excluded from a treatment such as a campaign.

A comparison group deliberately excluded from a treatment such as a campaign.

## An example

An experiment withholds an ad from a randomly selected eligible group to estimate incremental conversions.

## Why it matters

Valid comparisons require appropriate assignment, sufficient evidence and controls for contamination.


## Related terms
- [A/B testing](https://jolts.xyz/resources/glossary/ab-testing)
- [Conversion tracking](https://jolts.xyz/resources/glossary/conversion-tracking)
- [Incrementality](https://jolts.xyz/resources/glossary/incrementality)

## Next step

[Explore advertising](https://jolts.xyz/advertisers) or [monetize your AI app](https://jolts.xyz/publishers).