Choose metrics in Feature Experimentation

Metrics are a quantitative measure of the success of your experiment. They tell you whether the variations in an experiment are winning, losing, or inconclusive based on changes in visitor behavior in response to your experiment.

For example, suppose your site has an Add-to-Cart button. You would use an event to track every time the button is clicked. You would use a metric to measure the percentage of users who added to the cart at least once or the average number of items added per user.

The primary metric is the one Optimizely Feature Experimentation uses to determine a statistically significant winning or losing variation. It is the most important goal of the experiment, and it decides whether your hypothesis is proven or disproven. In Optimizely Feature Experimentation, the primary metric achieves statistical significance at full speed, regardless of any other goals or events added. Additional metrics are called secondary or monitoring metrics. Select secondary metrics that give you insights into long-term success. See Primary metrics, secondary metrics, and monitoring goals for information.

Identifying the correct metric is a huge factor in determining whether your experiment has statistically significant results. See the following support articles:

Optimizely Feature Experimentation creates metrics by aggregating events over time. Directly track actions like clicks, pageviews, form submissions, purchases, and scroll depth. After you create an event and add it to an experiment, you decide how it is displayed as a metric.

Every Optimizely Feature Experimentation experiment needs at least one metric. You can add or modify metrics at any time.