The Skeptic's Four Trap Cards
Recall the key question for four common data-skepticism traps.
Correlation vs causation When two lines move together Ask: what else changed, and what comparison would isolate the mechanism? Use when a chart says a project, feature, or policy caused a metric to move. Survivorship bias A stakeholder says, 'Our best customers all did this.' The winners prove the practice works. Your line Let's also look at everyone who started, including the customers who did this and still churned. Interviewing only winners turns evidence into biography. It restores the missing denominator without dismissing the success stories. Alert count vs probability Base-rate check Counts become useful when paired with prevalence. Simpson's…
Sign up free — one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in