About Incrementality Calculator
Who makes the site, where the numbers come from and how the maths works.
Incrementality Calculator teaches incrementality with interactive labs and guides, and is made by Linkrunner. Every number about Forkly and the sample channels is invented to show the method. Real-world platform facts come from official pages read on 26 Oct 2026.
Who makes this site, and how it works
Who makes this site
Linkrunner made Incrementality Calculator to explain incrementality: what it is, how to test it and how to read the result, with labs you can move rather than slides you read.
Linkrunner is an AI-driven mobile measurement partner (MMP) that unifies attribution, deep linking and SKAN in one platform for mobile growth teams.
- Organic attribution included: organic and attributed installs sit side by side, which is the starting point for any incrementality test.
- Open data: unrestricted CSV, API and webhook exports.
- Free plan: 25k one-time attributed installs, no credit card, every feature included.
- Used by 400+ apps.
Website · Docs · Blog · Create a free account · Book a demo
The labs and guides teach a method, not a product: they work the same whichever MMP or ad platform your data comes from, and other vendors are described neutrally.
Sample data statement
Sample data: a made-up app to show the method, not a benchmark. Forkly is a made-up food delivery app. Every number about it on this site is invented to teach the method. The two channels in the ROAS lab and the pre-filled lift test are invented in the same way. Nothing on the site is a benchmark, an industry average or a customer result.
How the maths works
- Lift and its interval: two-proportion normal approximation without pooling, 95% confidence (z = 1.96). The lift interval divides the difference interval by the control rate, treating the control rate as fixed.
- p-value: two-sided, from the same z score.
- Test sizing: the standard two-proportion sample size formula for 95% confidence (two-sided) and 80% power, with unequal group sizes.
- Simulation: daily installs in each group are drawn from a normal approximation to the binomial with a seeded random generator, so every draw is reproducible.
- Assumptions: people are split at random, one person's choice does not affect another's, and the control group is not reached by the ads. Real tests break these in ways the labs do not model, such as people seeing ads on another device or region.
Each lab's calculations run in your browser and match a separate Python implementation used to build the page. Nothing you enter leaves your browser.
Corrections
Questions
Who makes Incrementality Calculator?
Linkrunner, a mobile measurement partner (MMP) for app growth teams, made it to explain incrementality with labs and guides. The labs teach a method that works the same whichever MMP or ad platform your data comes from.
Why does the site use a made-up app?
Because incrementality is easiest to learn when you can see the true answer and watch a test try to find it. Real campaign data never shows the true answer, and invented numbers dressed as real results would mislead.
Where do the platform facts come from?
From Google's and Meta's own help and developer pages, read on 26 Oct 2026 and linked on the platform guide. Anything we could not find on an official page is left out.
How do I report a mistake?
Email hello@incrementalitycalculator.com with the page and what is wrong. Maths corrections are checked against the worked examples behind each lab.
What is incrementality in app marketing?
Incrementality is the share of conversions that would not have happened without the ad. It is measured by comparing people who could see the ads with a similar group who could not, so it captures what the ads changed rather than what they were credited with.