← Coinbase Interview Insights

Coinbase·Data Scientist·Technical Phone Screen·Senior

SeniorPrefer not to say
May 2026Remote

Summary

Coinbase data scientist interview with a meaty experiment design question that went deeper than I expected. The second half about diagnosing a lift discrepancy is where things got interesting and honestly a bit uncomfortable.

Questions Asked (1)

Q1

Design an A/B test to evaluate whether personalized marketing emails increase purchase conversion rates. Walk through your choice of primary and guardrail metrics, the statistical test you'd use, how you'd set the minimum detectable effect, and how you'd calculate sample size and test duration. Then: after you roll this out to the full user base, a new director reruns the experiment and sees only a 2% lift where the original test showed 20%. What could explain that gap and how would you diagnose it?

A/B Testing & ExperimentationRoot Cause AnalysisProduct Analytics & Metrics
Author's notes

The first part felt fine.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Structure your answer by first outlining the experiment design (metrics, statistical test, MDE, sample size/duration) and then addressing the post-rollout discrepancy. Emphasize the importance of guardrail metrics, power analysis, and potential biases like novelty effects or selection bias. For the diagnosis, systematically consider internal and external validity threats and propose concrete checks.

Pro tip: When explaining the discrepancy, highlight that the original test may have suffered from novelty effect or selection bias, and suggest running a holdback experiment to isolate the true effect. Also, mention that segment-level analysis can reveal heterogeneous treatment effects that explain the diluted lift.

1. Define Metrics

Choose primary metric: purchase conversion rate. Select guardrail metrics: revenue per user, unsubscribe rate, complaint rate, and engagement metrics to ensure no negative impact.

2. Design Statistical Test

Use a two-sample proportion test (e.g., Z-test) for conversion rate. Consider sequential testing or Bayesian methods if peeking. Set significance level (α=0.05) and power (1-β=0.8).

3. Determine MDE and Sample Size

Set MDE based on business relevance (e.g., 5% relative lift). Calculate sample size using power analysis formula for proportions. Estimate duration based on daily traffic and allocation.

4. Diagnose Post-Rollout Discrepancy

Investigate potential causes: novelty effect, selection bias, external validity, implementation differences, or segment heterogeneity. Propose checks: holdback experiment, segment analysis, and comparison of test and rollout populations.

Key Points to Mention

  • Primary metric: purchase conversion rate; guardrail metrics: revenue, unsubscribe rate, complaint rate, engagement.
  • Statistical test: two-sample proportion test; consider sequential testing if peeking.
  • MDE: set based on business impact; use power analysis to calculate sample size.
  • Sample size formula: n = (Zα/2 + Zβ)^2 * (p1(1-p1) + p2(1-p2)) / (p1-p2)^2.
  • Duration: sample size divided by daily traffic; ensure full business cycles.
  • Discrepancy causes: novelty effect, selection bias, external validity, implementation differences, segment heterogeneity.
  • Diagnosis: holdback experiment, segment analysis, check for Simpson's paradox, compare test and rollout populations.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.