ab-testing

Calculate A/B test sample size by inputting your baseline conversion rate, minimum detectable effect, significance level, and statistical power to determine the exact test duration and valid sample size needed.

Structure A/B testing hypotheses using a clear framework that defines the growth experiment, selects primary and secondary metrics, and establishes guardrails to ensure valid and measurable conversion rate optimization results.

Yes, you can run multivariate tests and A/B/n tests using this experimentation framework, which supports planning and analyzing multiple variants to determine the best performing option with statistically valid results.

Analyze A/B test results by comparing variant performance against your predefined baseline metrics. Use the provided templates to document test plans, performance metrics, and final results for your growth experimentation program.

Track primary, secondary, and guardrail metrics when planning a website funnel A/B test. This ensures comprehensive measurement of your homepage, pricing, or signup page variants without negatively impacting overall user experience.

Avoid A/B testing when your website lacks sufficient baseline traffic to reach the required sample size, or when the minimum detectable effect is too small to achieve statistical significance within a viable test duration.