Attribution assigns credit for an observed outcome according to a rule. For example, a system might connect a paid visit to a recorded advertising interaction within a defined time window. That can help explain a customer journey, but the answer depends on the data available and the attribution rule.
Incrementality asks a different question
How many of those outcomes would not have happened without the activity? Answering that requires a credible estimate of what would have happened otherwise. An appropriate controlled experiment is one route; other comparison designs need their assumptions and limitations explained.
Before and after is a change, not proof
A busy week after a website update is encouraging, but the update may not be the only thing that changed. Weather, seasonal demand, staffing, promotions, repeat customers or nearby events can affect bookings. A simple before-and-after comparison should be described as a change, not proof of lift.
Small shops and small numbers
Small shops can also have too little data for a precise experiment. More decimal places do not solve that problem. A useful result may be "not enough evidence yet", with a plan for collecting better data or reviewing a longer period.
OwnerCue's local visibility report is not a causal sales measurement tool. Today OwnerCue can check whether a business has the data a fair test would need; it does not measure lift. Its longer-term measurement direction is intended to keep this distinction.
