Do I need to install anything?

No. It runs in any modern browser, free, with no account required.

For Engineers · A/B Test

A/B Test for a distribution fit

Built for engineers using it for real design work. Go from concept to a running model in the browser, then scale to the cloud when needed. Simulate a distribution fit live below — adjust the inputs and watch it respond, right in your browser.

A/B Test SignificanceLive

two-proportion z-test

Controls

Presets

A visitors

A conversions

B visitors

B conversions

An A/B test compares two conversion rates to see if a difference is real or just noise. The two-proportion z-test pools the data to estimate the standard error, then a p-value below 0.05 signals a statistically significant difference. Bigger samples separate the two curves and make small lifts detectable.

▶ Run in Python

Data Inspector

Rate A10.00%

Rate B12.50%

Lift+25.0%

p-value0.0769

Resultnot significant

Governing equation

z = \frac{p ^ _{B} - p ^ _{A}}{p ^ ( 1 - p ^ ) ( \frac{1}{n _{A}} + \frac{1}{n _{B}} )} = \frac{0.025}{0.113 \cdot 0.887 ( \frac{1}{1000} + \frac{1}{1000} )} = 1.77

Reading this result: B looks 25.0% different, but with only 2,000 visitors p=0.077 — the sample is too small to call it real yet.

Runs locally in your browser — free forever. Scale to the cloud when reality gets heavy.

or unlock everything with Pro →

Also for:Students Researchers Educators Hobbyists & Makers K-12 Students First Responders General version →

More with A/B Test

A/B Test for an A/B test A/B Test for a survey sample A/B Test for a poll margin A/B Test for a quality-control chart A/B Test for a clinical trial A/B Test for a customer churn A/B Test for a click-through rate A/B Test for an exam-score curve

Frequently asked questions

Is this good for engineers?: Yes — this version of "A/B Test for a distribution fit" is framed for engineers using it for real design work. Go from concept to a running model in the browser, then scale to the cloud when needed.
Do I need to install anything?: No. It runs in any modern browser, free, with no account required.