Incrementality asks a simple question: what happened because of our marketing that would not have happened otherwise? It sounds obvious, but many reports do not answer it. They show results that happened after a campaign, not results that happened because of it. The difference matters when you decide where to spend.
An everyday example
Imagine you run ads to people who have already visited your website. Many of them buy, and the ads look very successful. But some of those people were going to buy anyway. The true value of the ads is only the extra sales they caused, not all the sales that followed them.
How incrementality is measured
The basic idea is to compare a group that saw your marketing with a similar group that did not. Any difference in results between the groups is a fair estimate of the extra impact.
- Holdout tests: a random part of your audience is not shown the campaign.
- Geographic tests: a campaign runs in some regions but not in similar others.
- On and off tests: activity is paused for a period and results are compared.
- Platform lift tests: some ad platforms offer their own testing options.
Things to keep in mind
Incrementality tests need careful planning. The groups must be genuinely comparable, and the test must run long enough to show a real difference. Small audiences can make results unreliable. It also helps to agree in advance what you will do with the answer, whatever it turns out to be.
Why it is worth the effort
Understanding incrementality helps you avoid paying for results you would have had anyway. It can also reveal channels that look weak in standard reports but actually drive real growth. You do not need to test everything. Start with your largest or most uncertain areas of spend.
Asking “what would have happened anyway?” is one of the most useful habits in marketing. If you would like help designing a sensible test, have a conversation with the Northpeak team.
