How to read a chart or a headline somebody else made and find the place where it misleads: truncated axes, percentage points, relative risk, chart geometry, rates versus counts, survivorship, cherry-picked windows, regression to the mean, Goodhart's law, false precision, error bars, provenance, missing denominators, averages of averages, pie charts, absent comparisons, and working a headline back to its study. Then the machinery a chart is built from and every place a choice hides in it: log axes, two scales in one frame, uneven time axes, where the class boundaries fall, trailing averages and their lag, seasonal comparisons, a falling rate against a rising level, index base years, the basket behind a composite, the ecological fallacy, breaks in a series, and choosing which of these checks a given claim actually calls for. Scoped against statistics, probability and modeling, which own correlation versus causation, Simpson's paradox, the base-rate fallacy and extrapolation respectively.
Free to start · adaptive placement finds your level · reviews timed to your own forgetting.
Every idea is taught with motivation and a worked example before the drills, and an FSRS spaced-repetition engine schedules each review for the day its model predicts you would forget it. A short placement check finds what you already know, so you start Data Literacy exactly where it's useful.