Incrementality experiments establish what's causing businesss outcomes. If a marketing tactic is incremental, it means it's causing business outcomes that wouldn't have happened otherwise.

For more on this, check out Episode 1 of Incrementality School: What is Incrementality? When you're ready to go a smidge deeper, we recommend this article on Incrementality Fundamentals.

Say you're trying to optimize your channel mix. Incrementality testing can help you answer:

• Which new channel should we invest in?
• Are we spending the right amount on each channel?
• How should we reallocate spend during holiday or promotional periods?

Incrementality tests don't just help with larger strategic decisions. They also help answer more granular, campaign-specific questions, like:

• Should we include or exclude branded search terms in our PMax campaign?
• Are UGC or polished brand ads more incremental for our brand?
• What's the right ratio of top-of-funnel and bottom-of-funnel media?

In the words of Haus Customer Marketing Lead Madde Dault, “Most of the major media buying and media planning questions that you’ve been circling for a while can be answered with incrementality tests."

Great question. Because incrementality is unique to your business, bands can't rely on benchmarks or others' tests – what works for one brand may not work for another. Test for yourself.

Designing the right experiment roadmap to answer your business questions is key to getting value from incrementality.

Reporting, goaling, and budget allocation should all be grounded in incrementality. Optimizing marketing for incrementality improves your P&L and drives efficient growth.

Think of incrementality experiments as the connective tissue between marketing and finance.

So autocorrect is driving you crazy, too? If anyone has any connections to the Oxford New American Dictionary, we'll take the intro (seriously).

You can measure incrementality by setting up a holdout test. This might involve running a nationwide marketing campaign in which 80% of the country sees the campaign and 20% doesn’t. The 80% audience segment is known as the treatment group, while the 20% audience segment is known as the holdout group. (You also might know it as the control group.)

Then you compare conversion data in these two groups to determine the incremental lift of your marketing campaign. You can calculate incremental lift using the following equation.

(Treatment group conversion rate — Holdout group conversion rate) ÷ Holdout group conversion rate

So, if the treatment group converts at a rate of 0.05 and the holdout group converts at a rate of 0.02, your campaign's incremental lift would be 1.5. In more readable terms: Customers were 150% more likely to convert if they saw the ad, meaning the campaign was incremental.

For more, check out the 'How do I measure incrementality?' section of Incrementality Fundamentals.

Incrementality testing measures the causal impact of a marketing activity. What would have happened if we hadn't run this campaign? By establishing a counterfactual, incrementality testing measures the additional value generated from the marketing activity.

Attribution assigns credit to different channels and touchpoints. Which channels contributed to this conversion? It distributes credit across channels or tactics – often in the form of views, clicks, or impressions – but doesn't measure if the conversion would have happened without the marketing activity. Attribution doesn't measure causality.

Marketing mix models (MMMs) are statistical models – often regression-based – that aim to quantify the impact of marketing and non-marketing variables (like seasonality or pricing) on business KPIs (like sales or conversions). Importantly, they use historical aggregated data to feed the model. Traditional MMMs can be helpful in illustrating correlations, but won't explain what caused or will cause business outcomes.

Incrementality testing measures how a change in tactics impacts a change in outcomes. Haus' Causal MMM is built on incrementality test results, meaning it's fundamentally powered by causal data that can provide more accurate recommendations on budget allocation and business decisions.

Geo-tests, holdout tests, and incrementality tests are all related, but they aren't quite synonymous. Geo-testing and holdout testing both refer to incrementality testing techniques, while incrementality testing could theoretically be conducted using a variety of techniques. At Haus, we are partial to geo-testing with holdouts to measure incrementality.

A/B testing compares two variants side by side, measuring which one is more effective. Incrementality gets at the causal impact of a marketing tactic by creating one group that receives the tactic and one group that doesn’t, isolating how business outcomes would differ in the absence of that tactic.

For more on this, we recommend checking out this article.

Yes. If It's geo-segementable, it's eligible for incrementality testing.

Learn how Haus helps brands measure the incrementality of offline campaigns like billboards, regional, linear TV, store openings, and out-of-home (OOH) activations with Fixed Geo Tests.

Incrementality is a continuous practice. It's not a once-or-twice-and-done thing – because incrementality experiments represent a point in time, you're never "done" testing. There is always something new to test, learn, and optimize. High-velocity testing = more learnings = better business decisions.

Not having an incrementality test running is a missed opportunity to run an efficient business.