Control group
In this context, the leads that never came from the channel you changed. Your bid strategy cannot touch them, so whatever happens to them is what the market, the season and your sales team did.
Why it matters
It is what turns a before-and-after into evidence. Google improving 28% while everything else improved 26% means you did nothing; 28% against a 4% fall is a result.
What goes wrong
It is not a randomised experiment and should not be described as one. Leads from Google and leads from elsewhere are different kinds of buyer, so this is a strong signal rather than proof. For proof, run a campaign experiment that splits the same traffic in two.
What this product does about it
25 resolved deals either side of the switch before any comparison is shown, and the control is named and counted rather than assumed.
Next to this
- Attributable liftThe part of an improvement the change can actually be credited with: the gap between how the affected group moved and how the control moved.
- CounterfactualWhat would have happened without the change.
- IncrementalityWhether the conversions credited to a channel would have happened anyway.
The rest of this step
Measure this on your own data
The diagnostic reads a CRM export in your browser and reports your volume, your match rate and the spread between your leads against the thresholds in this glossary. Nothing is uploaded and no account is needed.