What is incrementality?
Incrementality measures the additional conversions or revenue caused by a marketing activity. It separates ads that drive new revenue from ads that merely harvest existing demand.
Server-side conversions · true incremental lift validation · reconciled to Stripe · live in 30 minutes.
Definition
Incrementality measures how much a marketing activity actually caused — the additional conversions or revenue that happened because of an ad and would not have happened otherwise. It separates ads that drive genuinely new revenue from ads that merely take credit for conversions that would have occurred anyway. Where attribution asks "who gets credit?", incrementality asks "did this ad change the outcome at all?"
How incrementality is measured.
Incrementality is measured by comparing an exposed group against a control (holdout) that didn't see the ad — the counterfactual. Common methods include:
The quantities you are looking for are calculated as:
Incremental Conversions =
Conversions (Exposed) − Conversions (Control)
Incremental Lift % =
Incremental Conversions ÷ Control Conversions
Because it relies on a controlled comparison rather than a single tracked path, incrementality is measured periodically through experiments — not calculated continuously from one formula the way ROAS is.
Incrementality example.
Run a campaign to a test group, holding out an equivalent control:
The ad was credited with 1,000 conversions — but only 200 were truly incremental. The other 800 would have converted anyway. A channel can look great in attribution and still have low incrementality.
Why incrementality matters for attribution.
Attribution assigns credit for conversions you observe; incrementality tests whether those conversions were caused. The gap between them is where budget gets wasted. Branded search and retargeting are classic examples: they show high attributed ROAS because they intercept people already on their way to converting — but their incremental lift can be low, because much of that revenue would have arrived without the ad.
The practical answer isn't to pick one over the other — it's to use both. Reconciled, revenue-based attribution is what you run day to day to allocate budget across channels; periodic incrementality tests validate that the channels attribution rewards are genuinely adding revenue, not just harvesting demand. Attribution tells you where credit landed; incrementality tells you whether it was earned. (The full attribution guide →)
Questions, answered.
Everything teams ask before switching their attribution to Stripe truth. Still curious? Talk to us.
Incrementality measures the additional conversions or revenue caused by a marketing activity — the outcomes that would not have happened without it. It isolates the true causal impact of an ad from conversions that would have occurred anyway.
By comparing an exposed group to a control (holdout) that didn't see the ad, using randomized holdout tests, geo experiments or conversion-lift studies. Incremental lift is the difference in conversions between the two groups.
Attribution assigns credit for conversions you observe; incrementality tests whether those conversions were actually caused by the ad. A channel can have high attributed ROAS but low incrementality if it harvests demand that already existed.
Incremental lift is the percentage increase in conversions from the exposed group over the control: (exposed conversions − control conversions) ÷ control conversions. It quantifies how much the ad genuinely added.
Attributed ROAS can overstate impact by crediting conversions that would have happened anyway. Incrementality reveals the true, causal return — so you don't over-fund channels that merely intercept existing demand.
Ready to see which ads actually pay?
Start free, connect Stripe in 30 minutes, and get attribution that reconciles to the cent.
- Free to start — no credit card
- Live data in 30 minutes
