A/B Test Statistical Significance Calculator

A/B Test Statistical Significance Calculator Find out if your A/B test results are real — or just luck. Enter your control and variant data and get instant p-values, confidence intervals, and relative uplift. No signup, no data collection, no network requests. Everything runs locally in your browser. What it does This extension gives you a lightweight A/B test calculator that lives in your browser toolbar. Click the icon from any tab to: - Enter visitor and conversion counts for your control and variant groups - Choose your confidence level (90%, 95%, or 99%) - Get a clear verdict: statistically significant or not - See the p-value, relative uplift, control rate, and variant rate at a glance - View the confidence interval for the true difference in conversion rates Results appear instantly. No page loads, no waiting, no context switching. Why install it If you run A/B tests — on landing pages, ad creatives, email subject lines, checkout flows, or anything else — you need to check statistical significance before making decisions. Most people either skip this step or have to dig through bookmarks to find a calculator. This extension puts the calculator one click away, on every tab. You can check results during a meeting, while reviewing analytics, or while writing a test report — without leaving the page you're on. Who it's for - Growth marketers and CRO specialists running split tests - Performance marketers evaluating ad creative tests - Product managers reviewing experiment results - Data analysts who want a quick sanity check - Anyone who runs A/B tests and wants to make decisions based on evidence, not guesswork How it works The calculator uses a two-proportion z-test — the standard frequentist method for comparing two conversion rates. It calculates: - p-value: The probability your result happened by chance, assuming no real difference between control and variant. A p-value below your threshold (e.g., 0.05 for 95% confidence) means the result is statistically significant. - Relative uplift: The percentage difference between variant and control conversion rates. - Confidence interval: The range within which the true difference in conversion rates likely falls. It also warns you when your sample size is too small (fewer than 30 conversions per group), so you know when results may be unreliable. Privacy This extension collects no data. It makes no network requests. All calculations happen locally in your browser. There are no analytics, no tracking, and no third-party scripts. Built by Jarrah Agency Jarrah is a performance marketing agency that builds paid media and CRO programs on rigorous testing methodology. This calculator is the same one available on our website at jarrah.agency — packaged as an extension for quick access.