BECAUSE [what you observed, the evidence]
WE BELIEVE [changing X to Y]
WILL CAUSE [this specific metric to move by roughly this much]
FOR [this specific group of users]

WORKED EXAMPLE

BECAUSE 61% of people who abandon the signup flow do so on the delivery-slot step, and 9 of 12 user sessions showed confusion about whether slots were guaranteed,
WE BELIEVE showing a confirmed delivery window with a named date instead of a generic "choose a slot" picker,
WILL CAUSE signup completion to rise from 3.2% to at least 3.6% (a relative lift of 12%),
FOR first-time visitors on mobile.

Each part does a job. The BECAUSE forces you to have evidence, which kills ideas that are really just preferences. The WILL CAUSE forces a number, which determines your sample size and prevents post-hoc reinterpretation. The FOR forces you to name your population before you see the data, which is what stops you slicing your way to a result in Chapter 8.

The Number in "WILL CAUSE" Is Not Optional

Without an expected effect size you cannot calculate a sample size, which means you cannot know how long to run, which means you'll stop when the result looks good. That one omission causes more bad decisions than any other single mistake in A/B testing.

A/B Testing for Product Managers

Module 1Why Most A/B Tests Waste Three Weeks

Module 2Is This Even Worth Testing?

Module 3Writing a Hypothesis You Can Be Wrong About

Module 4Choosing the Metric

Module 5How Long It Needs to Run

Module 6Running It Without Ruining It

Module 7Reading the Result

Module 8Deciding and Shipping

Module 9The Six Ways Tests Lie

Module 10When A/B Testing Is the Wrong Tool

Module 11Final Project: Design, Run and Report One Real Test

Module 12Appendix: The Prompt Library

Module 13Glossary: Words Explained

The Four-Part Hypothesis