Xavier Fok

There is no row count that makes a number trustworthy. Enough depends on the size of the difference you are chasing, and a large sample of the wrong people is worse than a small sample of the right ones.

A parsing bug hid in my price scraper for 19 days. The fix took one afternoon, and it only took one afternoon because the raw pages were still sitting on disk untouched.

Two things moving together does not mean one caused the other. How confounders and small samples fool founders, and the habits that keep you honest.

Lagging indicators report a result you can no longer change. Leading indicators move first. Here is how to pair a couple of each without getting fooled.

Data governance for a one person business, stripped down to a few light rules that keep your numbers honest and make a future handoff painless.

The SaaS quick ratio compares the recurring revenue you add to the revenue you lose. Here is how to read it and where it misleads a small business.

Survivorship bias makes your numbers lie by hiding what failed. Here is how to spot the missing data and read your business metrics honestly.

AI can clean and categorize messy business data in an afternoon, but it fails quietly. Here’s where it saves hours and how to check its work.

Active users come in daily, weekly, and monthly counts. Here’s what each window tells you, how the stickiness ratio works, and the common misreads.

A tracking plan is a written list of every event you record, what it means, and its properties. Here’s how to build one before your analytics turns to mush.