Incrementality & lift calculator
Enter the conversion rate of your exposed test group, the conversion rate of your holdout control group, the test group size, value per conversion, and spend. You get lift, incremental conversions, and incremental ROAS.
Lift of 23.1% · iROAS 2.00×
- Relative lift
- 23.1%
- Incremental conversions
- 300
- Incremental value
- 18,000.00
- iROAS
- 2.00×
iROAS counts only conversions the ads caused, so it is almost always lower than platform ROAS. This does the arithmetic, not the significance test — check that the difference is statistically real.
How it works
An incrementality test splits your audience into a test group that sees the ads and a holdout control group that does not. The control conversion rate is your counterfactual: what would have happened without the ads. Comparing the test rate against the control rate isolates the causal effect from conversions that were going to happen anyway.
Lift is the test rate minus the control rate, divided by the control rate. A 2.4% test rate against a 2.0% control rate is a 20% lift. Incremental conversions scale that difference to your audience: the test rate minus the control rate, times the test group size. Those are the conversions the ads actually caused.
iROAS is incremental conversions times value per conversion, divided by spend. This is the return on only the conversions the ads created, which is why it is almost always lower than platform-reported ROAS. It is the number that answers whether the channel deserves the budget, not just whether it gets credit.
Assumptions and limitations
- This calculator does the arithmetic but not the statistics. Small groups or small rate differences can produce lift numbers that are pure noise; check significance before acting.
- Results are only valid if the holdout was randomly assigned and genuinely unexposed. Contaminated holdouts, such as users reached on another device, bias lift downward.
- Lift measured during the test window may miss delayed conversions, and short tests can overweight or underweight seasonal effects.
- A single test measures that channel, audience, and period. Incrementality is not a fixed property; it changes with spend level and saturation.
Frequently asked questions
What is incrementality in marketing?
Incrementality is the portion of conversions that your advertising actually caused, as opposed to conversions that would have happened without it. It is measured by holding out a randomized control group from the ads and comparing conversion rates. Attribution assigns credit; incrementality measures cause, and the two can disagree dramatically.
How do you calculate incremental lift?
Subtract the control group conversion rate from the test group conversion rate, then divide by the control rate. If the test group converts at 3.0% and the holdout at 2.5%, lift is 20%. Multiply the rate difference by the test group size to translate that into incremental conversions.
What is iROAS?
iROAS is incremental return on ad spend: the value of only the conversions the ads caused, divided by spend. It is calculated as incremental conversions times value per conversion, divided by spend. Because it strips out conversions that would have happened anyway, it is a stricter and more honest efficiency measure than standard ROAS.
Why is my iROAS lower than my platform ROAS?
Platform ROAS credits the ads with every attributed conversion, including people who were already going to buy. iROAS only counts the conversions the ads caused, which is a subset. A large gap between the two usually means the channel is claiming credit for demand it did not create, often from retargeting or branded audiences.
Is my test data uploaded or stored by this calculator?
No. All calculations run client-side in your browser, and none of the rates, audience sizes, or spend figures you enter are transmitted or stored anywhere.
More free tools like this, by email
I publish new calculators and explainers regularly. Get them when they land — no spam, unsubscribe anytime.