Datalad calculator

Sample Size for Revenue and Other Continuous Metrics

Sizing a test on revenue per user is not the same problem as sizing one on conversion rate, and it needs a number most teams cannot look up: the standard deviation. This works it out from figures you already have.

1

What you are measuring

The first needs no database query
Per cent of users who order
Among people who order
Among people who order
Across everyone, including non-buyers
Across everyone. This is the number that matters
2

What you want to detect

Per cent, relative
Across all variants
Trims the tail, shrinks the spread
3

The answer

0
users per variant
0
users in total
0
weeks to run

Uses the standard two-sample comparison of means. The result is the sample size at which a test of this metric would reach the stated power.

View Comments (1)

Leave a Reply

Subscribe to My Newsletter

Subscribe to my email newsletter to get the latest posts delivered right to your email. Pure inspiration, zero spam.

Discover more from Discuss Data Science, Machine Learning and Analytics

Subscribe now to keep reading and get access to the full archive.

Continue reading