How does Mixpanel interpret the results in Signal?

“Opportunity” is Mixpanel’s proprietary calculation of how important a given correlation might be. Opportunity helps pare down results by eliminating false positives and highlighting weak correlations that may be actionable. Based on this assessment, which determines how much an event impacts conversion on your goal, Mixpanel will tell you if there is an opening to make a change in your product or not.

Once we have the correlation, the results on the summary page will display the optimal action, correlation with the goal event, and our key findings about that optimal action.

The optimal action tells you how many times and in how many days your customers should do the event in order to achieve your optimal correlation. Frequency labels are listed below the action and provide precise information, based on the correlation, about when your users should complete the event. For example, if you are a music streaming app and wanted to see how a “Play Song” event correlates with two week retention, you might see something like, “Play song once within ten days” as an optimal action.

Frequency Labels -- these will be supplemented with temporal labels, i.e. At least 4 times in 10 days.

  • Many times

  • Just once

  • At least x times

  • Always avoid

  • As few times as possible

  • No strong correlations found

  • Is complex

The correlation with the goal event presents to you the optimal correlation for the event and tells you whether this indicates a strong or weak association with your goal. We calculate the association using a well-known statistical measure called the phi coefficient. The phi coefficient is a single number between -1 and 1 that indicates how closely an event moves with your goal event.

Finally, we will display the key findings. The key findings contain the rarity analyses and the impact to conversion. The rarity analyses define how common or uncommon is it for users in your user group to complete your event and the impact to conversion explains how the event impacts conversion to your Goal event (i.e. retention). These help you interpret the correlations. A certain event may have strong correlation to a goal event but may not have been completed by many users in your group and thus is unlikely to be useful. Below we have listed the different messages you can see as a part of the rarity analysis and the impact to conversion.

Rarity Analyses

  • Rare in user group

  • Never performed in user group

  • Uncommon in user group

  • Common in user group

  • Majority of user group performed

Conversion Measures

No users converted to goal.

  • Example: None of the users analyzed converted to the goal in question.

Unlikely to be useful.

  • Example: There may be no correlation (positive or negative) between the two events.

Associated almost perfectly with not converting. Something might be off here.

  • Example: Users who trigger an “uninstall” event are not going to complete your Goal event.

Associated almost perfectly with . Too good to be true?

  • Example: Users who trigger a purchase event will always trigger an add to cart event. Add to cart and purchase will always have high correlation.