What is incrementality and why does it matter?

Marketers love a clean metric.

ROAS. CPA. CPC. CPM. Easy to calculate. Easy to report. Easy to believe. But here’s the problem: just because a metric is clean doesn’t mean it’s telling you the truth.

Hello incrementality. The unsexy, under-measured, but incredibly important question that every marketer should be asking: Would this result have happened if we didn’t spend the money?

Because ROAS might tell you what you got. But incrementality tells you what you caused. And there’s a very real difference between the two.

Wait, but what’s wrong with ROAS?

Let’s say you run a paid ad and get a bunch of conversions. You calculate your return on ad spend and think, "hell yeah, we crushed that". But did you really? Maybe some of those customers were already coming to you. Maybe some would’ve converted organically. Maybe the ad simply intercepted a decision that had already been made.

That’s the dirty little secret behind clean metrics: they can’t tell you what would’ve happened if you did nothing.

Incrementality asks a question that really matters. It’s about causality, not correlation.

It asks, "If we hadn’t spent this money, would the result still have happened?" It’s like the grown-up version of performance marketing. But it’s also… really hard. And that’s probably why more marketers don’t measure it.

A performance agency Ad Week spoke to said that less than 1% of their brand clients had proper incrementality testing in place. That means most marketers are flying blind, and over-attributing wins to paid efforts.

The cost of this? Misallocated budgets of 10–30%. That’s not just waste. That’s missed opportunity.

This is easy enough for me to talk about on paper, but what does measuring incrementality actually look like IRL?

It starts with:

• Media mix modelling (if you’re fancy or flush with data)

• A/B testing regions or audiences (exposed vs. control groups)

• Time-based pauses (turn spend off and watch what happens to sales)

• Geo-holdout testing (spend in one area, not in another, and compare)

It doesn’t have to be complex or expensive. But it does require discipline and a willingness to admit that some of your “wins” might not have been wins at all. And that’s okay! Because that’s an opportunity to pivot.

Basically, what I’m saying is: make your work to make a difference.

The marketing world is a little obsessed with the word “performance”, but how many actually test whether their performance mattered?

ROAS and CPA make you look good. But incrementality tells you if your marketing is actually doing its job. So next time you pull a report and see the numbers looking slick, ask yourself the hard question: would this have happened without us?

If you don’t know the answer, it’s time to find out.

-Sophie Randell, Writer