After the lift test: Make incrementality part of weekly PPC reporting
Ben Vigneron proposes translating lift-test results into channel-level multipliers and an incremental CPA column so weekly reports inform budget decisions. He separates platform conversion counts used for bidding from experimental estimates used for allocation, and recommends showing uncertainty and retesting stale results. His Northwind example and weekly holdout numbers are fictional illustrations, not observed campaign outcomes.
Search Engine Land · Published
Why make time for it?
Read this when a lift study has finished but reporting still ranks channels only by platform CPA. The article offers a concrete way to carry test findings into recurring decisions while exposing uncertainty.
What to look for
- Put each test estimate beside platform-reported conversions for the same population and period.
- Flag multipliers when spend, targeting or conversion definitions change, and avoid decisions from noisy single-week lift reads.
Keep in mind
The worked account and holdout figures are synthetic. A channel multiplier can drift and may not transfer to new spend levels; MMM-derived ratios and guesses for untested channels are weaker than a well-designed experiment.
Take this question into the article
Which budget decision would change if your weekly report showed an uncertainty range for incremental CPA?
The people behind the article
Explore their work and recorded contributions on PMC.
Authorship points are shared between coauthors. Experts receive credit for substantive contributions, not mentions. One work earns one award per person, including when it appears elsewhere on PMC. How recognition works
Read the original source.
Continue to Search Engine Land for the complete source and supporting material.
Read the original sourceReading notes reviewed 15 Nov 2026. The publication date above belongs to the original source.