Grace Ge

Grace Ge

Building systems for better decisions.

Building systems for better decisions.

Decision Systems Toolkit

A/B Test Calculator

Decision Systems Toolkit

A/B Test Calculator

Run statistically sound A/B tests.

Interpret results with confidence.


A lightweight, offline toolkit — no installation, no account.
Download once, open anytime in your browser.


Yours to keep.

Run statistically sound A/B tests.

Interpret results with confidence.


A lightweight, offline toolkit — no installation, no account.
Download once, open anytime in your browser.


Yours to keep.

COMPARE · SIZE · TEST


Compare two groups.
Size a test before you run it.
Check whether the difference is real.


Free · Open source · Runs locally

COMPARE · SIZE · TEST


Compare two groups.
Size a test before you run it.
Check whether the difference is real.


Free · Open source · Runs locally

Four practical tools for common A/B testing decisions.

Four practical tools for common A/B testing decisions.

What's Included

What's Included

Compare metrics, estimate sample size, and evaluate statistical significance.
Everything you need for common A/B testing decisions in one toolkit.

Compare metrics, estimate sample size, and evaluate statistical significance.
Everything you need for common A/B testing decisions in one toolkit.

01 · Mean Comparison

Compare continuous metrics such as revenue, order value, or time on page.

02 · Proportion Comparison

Compare conversion rates and other binary outcomes.

03 · Sample Size

Estimate how many observations you'll need before running a test.

04 · Statistical Power

Understand whether your experiment has enough power to detect a difference.

Use it or keep it

Use it or keep it

Open the A/B Test Calculator in your browser, or download it to keep.

✔ Includes both English and Chinese versions

✔ Runs locally in your browser

✔ No installation required

Open the A/B Test Calculator in your browser, or download it to keep.

✔ Includes both English and Chinese versions

✔ Runs locally in your browser

✔ No installation required

Open in Browser — English

Open in Browser — English

在线打开 — 中文

在线打开 — 中文

Or download a copy:

Version 1.0 · Released July 2026

Version 1.0 · Released July 2026

See the code

See the code

This tool is open source.

Every statistical function is written in plain JavaScript you can read and verify.

MIT licensed. Fork it, change it, use it in your own work.

This tool is open source.

Every statistical function is written in plain JavaScript you can read and verify.

MIT licensed. Fork it, change it, use it in your own work.

Systems in Practice

Three examples, three different moments where a test goes wrong.

Example 01

Three add-ons, one test.

Three completely different calls.

Two of them nobody celebrates.

Example 02

One trial-length test.

An 18.6% lift on paper.

A test that was never built to see it.

Example 03

One promotion, eight store types.

Two significant results.

Neither one was real.

Get Future Updates

I'm continuously improving the Decision Systems Toolkit.

If you'd like to hear about new tools, improvements, or future releases, leave your email below

I'm continuously improving the Decision Systems Toolkit.

If you'd like to hear about new tools, improvements, or future releases, leave your email below

(No spam. Product updates only.)

(No spam. Product updates only.)

Looking for something more structured?

Build Your Own Career Intelligence System

A guided implementation program for building a repeatable Career Intelligence System you own.

A guided implementation program for building a repeatable Career Intelligence System you own.

Built by Grace Ge

Built by Grace Ge

Building systems for better decisions.

Building systems for better decisions.

grace@gracege.com

© 2026 Grace Ge