📄 Article
✓ Link checked
Free
Intermediate
Why we picked it This is the vendor-neutral walkthrough of how to actually structure a pricing test so you can trust the result. It starts with a falsifiable hypothesis, forces you to change one variable, gets sample size right, and reads conversion, ARPU, and retention together instead of celebrating a single number. It also tells you plainly to keep existing customers on their current rate and think through what happens when people compare prices, which is the part most founders skip.
Pricing experiments: A guide for businesses
From Stripe by Stripe
- Change one variable and use a real sample-size calculation, or your higher-price result is just noise you talked yourself into believing.
- Judge the test on revenue per visitor and retention together, not conversion alone, because a lower price that converts better can still lose money.
- Test on new signups and treat it as a limited-time frame so current customers do not feel switched on mid-relationship.