Glossary · Money · also de-confounding
What is confounding?
Confounding is when a third factor drives both the behaviour being measured and the outcome, making an association look causal when it is not. In store analytics the most common confounder is traffic mix: a page that appears to convert badly may simply receive colder traffic than the pages it is compared with.
- Reviewed 6 October 2026
In more detail
This is why raw comparisons between pages, devices or cohorts are so often wrong. Mobile converts worse than desktop partly for mechanical reasons and partly because mobile traffic arrives from different sources with different intent.
The defences are comparison against a like-for-like slice of the store’s own traffic and, where the stakes justify it, randomisation, which removes confounding by construction rather than adjusting for it afterwards.
Key points
- Traffic mix is the most common confounder in store analytics.
- Raw page-to-page and device-to-device comparisons are usually confounded.
- Randomisation removes it by construction; adjustment only approximates.
How Liftable relates
Related terms
Guides that go deeper
Last reviewed against the product on 6 October 2026.
Scan your store.
See where your store is losing revenue and what to fix first. It is free, takes about a minute, and needs no install.