ab-test-analysis

To calculate A/B test statistical significance from a CSV export, the tool processes raw control and variant data to compute p-values, conversion rates, relative lift, and 95% confidence intervals for accurate product decisions.

You can determine if your sample size is adequate for A/B testing by running a power check. The analysis evaluates sample size adequacy, test duration, and randomization integrity to ensure your experiment results are valid.

Yes, you can analyze A/B test results with unequal traffic splits. The evaluation accommodates varying durations and traffic allocations across control and variant groups to accurately calculate conversion rates and statistical significance.

The best way to interpret p-values and confidence intervals for product experiments is through structured guardrail checks. This approach translates statistical metrics into actionable ship, extend, stop, or investigate recommendations for stakeholders.

To evaluate wash-out effects and randomization integrity in experiment design, the evaluation assesses your test setup. It checks for sample size adequacy and structural biases to validate the experiment environment before computing final statistics.