Skip to content

Holdout experiment

A holdout experiment splits an audience into a test arm that sees ads and a control arm that does not, then compares conversions to measure incremental lift.

Holdout experiment

A holdout experiment is the gold-standard incrementality measurement. The platform randomly assigns a portion of the audience to a control arm; the operator compares conversion rates between arms.

Why holdout

Attribution models estimate. Holdouts measure. The randomisation eliminates the selection bias that makes pixel-based attribution unreliable on iOS, in incognito, and after consent rejection.

What the platforms support

Meta supports Conversion Lift studies natively. Google supports geo and audience holdouts via Experiments. Both expose the random assignment via API; Ripplux reads the result and updates the ROAS engine.

What it costs

The control arm doesn't see ads, so the merchant gives up some conversions during the test window. The trade-off is a clean number that future budget decisions can rely on.

See how much of your ad spend is wasted

Ripplux is live on the Shopify App Store. Install free and see your own numbers, no charge for 14 days. While the founding cohort is open, founding stores lock Pro at $99/mo for life.

Start your free audit