Analyzing experiment results

Summary of A/B test course by Google on Udacity (Part 4)

  • Invariant metrics: Metrics should not change when you run experiment.
Captured from the course
Captured from the course
Captured from the course
  • Cons: Conservative because sometimes you will track metrics that are correlated and all tend to move the same time
  • Control false discovery rate (FDR)

Feral cat trying to make sense people and the world around