← marketing-mindset

A/B verdict calculator

Most read-outs answer one question (“which arm won?”) and skip two others: is the difference separated from zero, and is the volume above the floor the observed lift would need. This page answers all three, the same way the published CLI does (npx marketing-mindset verdict). Everything runs in your browser; nothing is sent anywhere.

1. The two arms

2. The read-out

3. What the three verdicts mean

not readable

The interval for the difference includes zero. More volume, a higher base rate or a bigger difference — not a rebuild.

a lead, not a verdict

The interval excludes zero, but the sample is below the floor the observed lift needs. Real signal, unreadable size: keep it running to the floor.

readable

The interval excludes zero and the volume clears the floor. This is the only state in which a number can be acted on.

4. Before the test starts

A verdict calculator only helps if the floor was checked first: how many sends an email test needs, the stop rule written before the first send, the tagged url and event name that make the arms comparable. The same arithmetic is in the job description page: a strict test at a 3% base rate needs 13,914 contacts per arm.

Written by Axel Freeman — marketing engineer. Telegram · llms.txt

Also: honest test queue planner — turn volume into a queue: the floor per arm, the days each test needs and the day each verdict lands.

Also: what one honest test costs to finish — the contacts a verdict needs, the days it takes and how many funded tests a budget carries.

Also: which step of your funnel can fund a verdict — the floor, the events each arm sees in a month, and the months a readable unit takes at your volume.

Also: which of your channels can actually fund a verdict — floor per arm, months to verdict, the cost of one full two-arm test and the channel to run first at your volume.