Module
Module 2 of 5Lesson 1 of 2~14 min

What a controlled test proves, and what an analysis does not

A metric that improves after a launch does not prove your feature caused it. This lesson explains what a controlled test establishes that everyday comparisons cannot, then sets up a shared vocabulary with data teams. You can then challenge a shaky impact claim before it steers the roadmap.

Take this lesson: your first course is freeSee the full syllabus

Lesson objective

By the end of this lesson, you will be able to explain why a pre/post comparison or a comparison between users and non-users does not measure the effect of a change, what randomization brings, and to use the vocabulary of an A/B test correctly (control, variant, unit, exposure).

Topics covered

  • A/B testing
  • causality
  • randomization
  • before-after comparison
  • control group

Where it fits

Should you test?

What does an A/B test prove that an analysis does not, and when is it better to do without one?

Lessons in this module

  1. What a controlled test proves, and what an analysis does not (this lesson)
  2. When not to test, and what to do instead

What you will learn in the course

This lesson is part of the course Design and analyze an A/B test

  • Decide whether an A/B test is the right method (volume, B2B, reversibility, time, ethics) and choose a suitable alternative otherwise.
  • Write a testable hypothesis, choose a sensitive, attributable primary metric, guardrails and the exposure event to log.
  • Choose the randomization unit and prevent interference between groups, including in B2B.
  • Compute a sample size and a duration from the baseline rate, the minimum detectable effect, the significance level and the power.
  • Analyze a result (p-value, confidence interval, practical significance, guardrails) and read a tool's Bayesian or frequentist output.
  • Detect and avoid analysis pitfalls (peeking, multiple comparisons, novelty effect, sample ratio mismatch, Simpson's paradox).
  • Decide based on rules written before the test and document the experiment in a reusable memo.

Related courses