Interesting weekend marketing science read: can MMM parameters be estimated from geo…
This is a marketing post classified by Jev as Analytics & attribution (a free resource), kept by the Marketing Radar because it carries real work, not commentary.
Interesting weekend marketing science read: can MMM parameters be estimated from geo tests? A data scientist at Zalando argues that geo tests contain more useful information than is often utilized, given that they tend to be reduced to mere ROAS estimates for use in MMM calibration. The paper makes the case that adstock decay, saturation, and effectiveness parameters can be estimated from treatment-control differences in geotest time series, thereby sidestepping the endogeneity problem faced in observational MMM, since randomization renders the groups comparable apart from tested-channel sp
Posted by Eric Seufert (49.1k followers) 19 days ago · 13 likes · 3.6k views · view the original post on X. Kept by the Marketing Radar as Analytics & attribution.
More marketing work like this
- hey @marclou — @tellenne_
- I just added a filter by @handle for Stalkr. — @marclou
- The internet is about to run out of truth. — @BeingAshwin
- NEW in @sparktorohq -- visitation by category, which means you can: — @randfish
- This is our biggest offer ever. — @northbeam
- "We're constantly looking for places to get answers, and Northbeam has been very easy… — @northbeam
- Marketing teams already have the data. The harder part is turning it into something they… — @databricks
- Surface-level questions get surface-level answers. — @ZetaGlobal
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 3.7k posts from 4.7k X accounts over the last 21 days, 116 tools, 13 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:46 UTC. Full method.