An advanced option before launching an experiment that allows you to review the experiment in an interactive manner.
Setting the size of an experiment’s population.
Attributes defined by you that can be used for targeting and segmentation.
A variant of an experiment that is the same as the original app.
End users or users
Users or consumers of the mobile apps that Apptimize supports
A specific piece of data with associated properties that we track in our analytics system.
Toggle that allows experiments to run in parallel with other experiments on a specific user’s device.
An A/B test that includes a control and variant(s).
Funnel conversion rate
Percentage of users who progressed through all steps of a funnel out of all the users who enter into a funnel by converting on the first step of the funnel.
Event or combination of events that measure the success of an experiment.
Taking an experiment live so that users will start participating.
Capability to turn off experiments or variants in real time so end users are returned to the stable default experience in case of bugs or risky releases. This can also be called a kill switch.
A way to select a subset of your users for an experiment.
A version of an app. Variants that you create are typically different than the original app.
The experiment variant that’s chosen to be rolled-out to all end users after an experiment ends
Number of unique users who triggered the event at least once.
Percentage of participants who have converted (i.e. fulfilled the goal at least once).
An expression using an attribute, operator, and criteria used to sift through data.
Raw change in conversion rate from control to variant.
Percentage better or worse a variant is compared to the control in an experiment.
Metric Value (in CSV export)
The metric value column in the exported results CSV file represents the value of the computed metric you selected. For instance, if you are measuring conversion rate of purchases as a goal, the metric value column shows the conversion rate calculated.
Number of Sessions
Number of sessions is how many foreground-to-background transitions that we see.
Number of times the goal event was triggered.
Occurrences per user
Average number of occurrences per participant.
A user in an experiment’s population who has seen a variant. We determine this by whether the mobile devices runs the code that determines variant treatment.
Apptimize bucketed the user into the experiment and one of its variants or control. This means that the user met the filtering requirements and were randomly selected according to your allocation. Some users will be enrolled but never “Participate” in a variant because they don’t navigate to the part of the app that contains the experiment.
The number of users who have a second session- open the app at least a second time, in a given period of time.
Screens Viewed per Session
On Android this is the number of activities, popups, and fragments we measure during a session. On iOS it is the number of view controllers shown that we measure per session. Note that since this is how we measure screens view, it’s possible given how differently apps are designed that we overcount the number of screens viewed, however since in an experiment you’re measuring versus a control this doesn’t adversely affect your experiment results.
A session is when a user is in your app, specifically measured by the time between when your app is foregrounded to when the app is backgrounded.
The session interval is time between consecutive sessions, specifically the time between when the app is backgrounded to when it is next foregrounded by a user.
Session length is measured by the length of time between a foreground and a background.
Standard method for statistical significance by confidence. Statistical significance is the probability that the difference in the goal metric between variant and control is not due to random chance. P value equals 1 minus statistical significance.
Direction of lift.
Total sum of all the numeric values associated with goal event.
Value per user
Total event value per participant.