Glossary · Management
Incrementality
The conversions that marketing caused, over and above those that would have happened without it, measured against a randomly held-out group or matched control regions. Platform- and retailer-reported conversions, by contrast, can include sales that would have happened anyway.
- Field
- Management
- Examined in
- CBA-DMP
- Learning objectives
- 2
Where the CBA Standards examine it
Digital Marketing ProfessionalCBA-DMP
- 6.4Select the measurement method for a stated decision, distinguishing attribution, incrementality testing and marketing mix modelling by the question each answers.Measurement, Attribution and Testing
- 6.5Calculate incremental conversions and cost per incremental conversion from a holdout or geographic test, and compare them with platform- or retailer-reported results.Measurement, Attribution and Testing
In the specimen paper
Nuqta Gadgets, an online electronics accessories retailer in Dammam, ran a month of retargeting ads with a randomised holdout: comparable recent site visitors were split at random into a group that could see the ads and a group that could not. Spend was SAR 24,000, and the ad platform reported 600 conversions. Exposed group | 40,000 visitors | 1,200 orders Holdout group | 10,000 visitors | 200 orders What was the cost per incremental conversion?
Answer
SAR 60, from 400 orders above the 800 the holdout rate predicts.
Why that is the answer
Incremental conversions are the orders the ads caused: what the exposed group did, less what it would have done without the ads, and the holdout supplies the second figure as a rate. Here 200 orders from 10,000 held-out visitors is 2 per cent, so the 40,000 exposed visitors would have placed 800 orders unprompted; they placed 1,200, so the ads added 400, at SAR 24,000 divided by 400, or SAR 60 each. The platform's 600 conversions imply SAR 40, and the true cost is half as much again, because the platform credits orders that would have happened anyway. Scale the holdout to the exposed group before subtracting, and judge spend on the cost per incremental conversion, not the cost per reported one.
Related terms
- Attribution modelManagement
A rule or algorithm for sharing credit for a conversion among the marketing touches in a customer’s journey: last-click, first-click, linear, position-based, time-decay or algorithmic. None is a controlled test of which conversions would have happened without the spending.
- A/B testTechnology
A controlled experiment comparing two versions of something by assigning users at random to each, so that a difference in outcome can be attributed to the change.
- Marketing mix modelling (MMM)Management
A statistical model that estimates each channel’s contribution to sales, offline channels included, from aggregate spend and sales over time, not individual journeys. It models carry-over, where advertising keeps working after it stops, and saturation, where extra spend returns less.