ab-test-setup

Calculate A/B test sample size by inputting your baseline conversion rate and minimum detectable effect (MDE) into the statistical planning framework. This determines the required traffic volume and test duration to achieve statistical significance.

Structure a conversion rate optimization hypothesis using a standardized observation-to-metric framework. This enforces statistical rigor by documenting the expected change, the target digital product metric, and the underlying rationale before test execution.

Analyze A/B test results using the post-test performance evaluation template to interpret data across digital product metrics. The framework enforces hypothesis documentation and guardrail monitoring to validate statistical significance and ensure reliable outcomes.

Use ICE scoring to prioritize your experimentation roadmap by evaluating test ideas across Impact, Confidence, and Ease dimensions. This system integrates with post-test analysis to help rank future digital product experiments effectively.

The framework supports both standard A/B experiments and multivariate testing. It facilitates the design and statistical analysis of both experiment types, allowing you to calculate requirements and evaluate performance across various digital product metrics.

Monitor guardrail metrics during experimentation to ensure statistical rigor and prevent negative impacts on overall digital product performance. This framework enforces guardrail tracking alongside your primary hypothesis to catch degradations in secondary metrics.