Analyze the results of product experiment: {{experiment_name}}. Experiment details: - Hypothesis: {{hypothesis}} - Primary metric: {{primary_metric}} - Sample size: {{sample_size}} - Duration: {{duration}} Analysis structure: 1. RESULTS SUMMARY | Metric | Control | Treatment | Delta | Stat Sig? | |--------|---------|-----------|-------|------------| 2. STATISTICAL VALIDITY - Sample size adequacy - Confidence interval - p-value interpretation - Effect size assessment 3. SEGMENTATION ANALYSIS - Did different segments respond differently? - Any surprising segment behaviors? - Interaction effects observed? 4. SECONDARY EFFECTS - Impact on related metrics - Unintended consequences - Guardrail metrics status 5. HYPOTHESIS EVALUATION - Was hypothesis validated or invalidated? - What did we learn? - What surprised us? 6. DECISION RECOMMENDATION - Ship / Iterate / Kill - Rationale for recommendation - Confidence level in decision - Risks of recommended path 7. NEXT STEPS - Follow-on experiments needed - Implementation requirements - Monitoring plan post-launch
Product Experiment Results Analysis
Analyze product experiment results and make data-driven decisions
47 copies0 forks
Share this prompt:
Details
Category
AnalysisUse Cases
Analyze experiment resultsMake shipping decisionsLearn from tests
Works Best With
gpt-4claude-3
Created Updated Shared