Permutation test
Also called Shuffle test.
Dealing the same deals into before and after at random, over and over, and counting how often chance alone produces a gap as large as the real one.
Why it matters
It answers the first question any analyst asks, using nothing but the advertiser's own rows. No distribution is assumed and nothing is simulated.
What goes wrong
Reported as a raw count rather than a p-value on purpose. Eighteen shuffles in a thousand matched this gap is a sentence anybody can apply their own standard to; p = 0.018 is a sentence that ends the conversation for most of the room.
What this product does about it
1,000 shuffles, seeded, so the same file always reports the same count.
Next to this
The rest of this step
Measure this on your own data
The diagnostic reads a CRM export in your browser and reports your volume, your match rate and the spread between your leads against the thresholds in this glossary. Nothing is uploaded and no account is needed.