Natural Experiment

Something you didn’t plan to test on the front end – when you established the testing hierarchy. For example, suppose that over a certain time period you mailed to a group of customers 3x. This wasn’t something you planned, it just happened. We’d call this a natural experiment and it can give us good directional data about the impact of frequency on sales behavior. Note that the results are directional only. Unless there is a random control group, use care when interpreting results. Customers who received a higher-level of frequency may differ in some important ways to those customers who received a lower-level of frequency.

Sharing is nice. Please share with a friend or colleague.