What is Incrementality Testing?

Incrementality testing measures the true causal impact of a marketing channel by comparing outcomes between a test group (exposed to marketing) and a control group (not exposed). It answers the fundamental question: "How many of these conversions would have happened anyway, without this marketing?"

How It Works

The most common approach is geo-experimentation: you split your target markets into matched pairs, run ads in the test markets, and suppress ads in the control markets for 2-4 weeks. The difference in conversion rates between test and control reveals the channel's true incremental lift. For example, if Facebook Ads drive a 15% conversion rate in test markets and control markets show 10% organically, the incremental lift is 5 percentage points — meaning one-third of Facebook-attributed conversions would have happened without the ads.

Why It Matters

Attribution models (even good ones) can't fully distinguish correlation from causation. A customer who clicks a branded search ad was probably going to buy anyway. Incrementality testing is the only way to measure true causal impact. Brands that run incrementality tests typically discover that 20-50% of their platform-reported conversions are not truly incremental — which means significant budget optimization opportunity.

How Attribution.ai Implements This

Attribution.ai provides built-in incrementality testing with geo-experiment design, automated result analysis, and channel-level incrementality factors. The system suggests which channels to test next based on where the biggest measurement gaps exist between your attribution model and expected incrementality.