Design an A/B test for a search ranking change
Last updated: October 13, 2025
Quick Overview
Design an experiment to test the impact of a redesigned homepage. Include sample size calculation, metrics, and analysis plan.
DE Shaw
October 13, 202559
7
2,361 solved
Design an experiment to test the impact of a redesigned homepage. Include sample size calculation, metrics, and analysis plan.
This statistics question from DE Shaw's Technical Screen tests your ability to apply mathematical reasoning to practical problems. The interviewer expects precise definitions, correct methodology, and awareness of assumptions and limitations.
What the Interviewer Expects
- Derive results from first principles when needed
- Handle complex scenarios with multiple interacting variables
- Design experiments that account for real-world complications
- Discuss advanced topics: Bayesian methods, causal inference, resampling
- Connect statistical concepts to business decision-making
- Identify subtle errors in reasoning (Simpson's paradox, survivorship bias)
Key Topics to Cover
How to Approach This
- Define your hypotheses (H0 and H1) clearly before performing any test.
- Calculate required sample size BEFORE running an experiment, using power analysis.
- Remember the Central Limit Theorem: sample means become approximately normal with large n.
- Watch for Simpson's paradox. Always segment data by key dimensions.
- Distinguish between statistical significance and practical significance.
Possible Follow-up Questions
- How would you handle multiple comparisons?
- What assumptions does this test make, and how would you validate them?
- What alternative statistical method could you use here?
- How would you explain this result to a non-technical audience?
Sharpen Your Skills on Codemia
Practice similar problems with our interactive workspace, get AI feedback, and track your progress.
Browse Statistics QuestionsSample Answer
Problem Formulation
To design an A/B test to evaluate the impact of a redesigned homepage on user engagement, we need to define our null and alternative hypotheses:
- H0 (Null Hypothesis): The redesigned homepage ha...
Solution Approach
- Determine the baseline conversion rate: Assume the current conversion rate (CR1) is 5% (0.05).
- Define the minimum detectable effect (MDE): Let's say we want to detect an increase in the ...
Submit Your Answer
