Case studies · done with Services · Measurement
22.8%of total sales, revealed by pausing Meta in seven statesGeo holdout · 7 states paused for 15 days · vs MMM estimate of 16.7%
What we found
Sales fell 22.8% in the states where Meta was paused. Meta drives more sales than the MMM estimated (16.7%) and far more than GA4 credited (near zero). The result now calibrates the model, and the Meta budget is planned on a number the business has seen with its own eyes.
Also a Meta for Business measurement case study.
Method
- 01
GA4 credited Meta with almost nothing, the marketing-mix model estimated 16.7% of sales, and Meta's own attribution claimed far more. Nobody could plan a budget on that spread.
- 02
We paused Meta for 15 days in seven states while comparable control regions kept running.
- 03
We compared sales in the paused states against the controls to measure what Meta had actually been contributing.
Run this test on your own account.
Start on EPYC →The growth operating system for your media: plan, run, measure, and improve every campaign from one place. Take it for a spin, on us.The platformBook a call →We run the models, design the experiments, and, if you want, your media too. You get the results. Thirty minutes with someone who does the work, not someone who sells it.The platform, humans included