Tool

    Incrementality Calculator

    Plug in your test and control group results to measure incremental lift, incremental CAC, and statistical significance, instantly.

    New to incrementality? Read the incrementality definition

    #
    #
    $
    $

    Your numbers

    Incremental Conversions
    110
    Test group outperformed control
    Incremental Lift
    26.8%
    Incremental CAC
    $72.73

    Rule of thumb: if incremental CAC is dramatically higher than your platform-reported CAC, the channel is over-credited and likely needs a budget cut.

    How to Calculate Incremental Lift

    Incrementality testing isolates the conversions your ads caused from the conversions that would have happened anyway. You hold out a matched control group from all advertising, then compare results.

    Incremental Conversions = Test Conversions − Control Conversions
    Lift % = (Test − Control) ÷ Control
    Incremental CAC = (Test Spend − Control Spend) ÷ Incremental Conversions
    
    Example:
     Test: 520 conv from $8,000 spend
     Control: 410 conv from $0 spend
     Incremental = 520 − 410 = 110 conversions
     Lift % = 110 / 410 = +26.8%
     iCAC = $8,000 / 110 = $72.73

    When to Run an Incrementality Test

    1. Scaling budgets beyond $50k/mosmall reporting errors become big dollar leaks.
    2. Launching new offline or top-of-funnel channels where click attribution doesn't apply.
    3. When platform CPA drastically disconnects from backend CAC.

    What is an incrementality test?

    An incrementality test (also called a lift study or geo-holdout) measures the true causal impact of advertising by comparing a group exposed to ads (test) with a matched group that was not (control). The difference between the two is the incremental conversions your ads actually caused, separating real ad-driven sales from sales that would have happened anyway.

    How do you calculate incremental lift?

    Incremental Lift % = (Test Conversion Rate − Control Conversion Rate) ÷ Control Conversion Rate. Incremental Conversions = Test Conversions − (Control Rate × Test Population). Incremental CAC = Test Spend ÷ Incremental Conversions.

    When is a lift test statistically significant?

    At a 95% confidence level, a two-proportion z-test result with |z| ≥ 1.96 is considered significant. If your sample sizes are small or the lift is marginal, you usually need more traffic or a longer test window.

    When should you run an incrementality test?

    Run incrementality tests on always-on channels (branded search, retargeting, Performance Max, broad prospecting on Meta) where platform-reported ROAS overstates true contribution. They are especially valuable post-iOS 14 as click-based attribution has become noisier.

    Not sure if your ads are actually driving growth?

    Book a free growth gap audit, we'll design a geo-lift or holdout test that gives you a defensible answer.

    Pressure-test your numbers on a free 30-min call

    Email me this lift result

    Send me your test and control numbers and I'll come back with a short note on whether the lift is real and what to do next.