ARPU Analyzer
A/B Test Confidence Calculator for Average Revenue Per User
Enter Test Data
Enter the data for your control and variation groups.
Results will appear here
Enter your test data and click "Calculate" to see the analysis.
About the Calculations
This calculator is designed to determine the statistical significance of an A/B test by comparing the mean Average Revenue Per User (ARPU) between a control group (A) and a variation group (B).
Statistical Method
The analysis uses a two-sample Z-test, which is appropriate for comparing the means of two independent groups, particularly with large sample sizes as is common in web and product experiments.
Assumptions
- Independence: The two groups (Control and Variation) are independent of each other. The behavior of a user in one group does not influence the behavior of a user in another.
- Sample Size: The sample sizes for both groups are large enough (typically n > 30) for the Central Limit Theorem to apply. This theorem states that the distribution of sample means will be approximately normal, regardless of the underlying data distribution.
- Variance Model (Poisson): The calculator assumes that the underlying revenue data follows a Poisson-like distribution, where the variance is equal to the mean. Therefore, the standard deviation for each group is calculated as the square root of its mean ARPU (σ = √µ). This is a common and simplifying assumption for revenue and conversion data.