A thread through the archive
Essays tagged “statistics”. Follow an idea across the archive.
Scott Alexander debunks claims of effectiveness for Vancouver's 'Don't Be That Guy' anti-rape campaign, arguing that the reported crime reduction is likely due to normal statistical fluctuations rather than the campaign's impact.
Scott Alexander argues for the value of using quantification and made-up statistics in decision-making, even when imperfect, as they often outperform intuition and reveal biases in our thinking.
Scott Alexander argues that generalizing male violence to all men is problematic, drawing parallels with racist generalizations about crime.
Scott Alexander examines the claim that '90% of medical research is false', arguing it's an exaggeration while acknowledging real issues in the field.
Scott discovers and shares links to the Bayesian Cabaret, a real biennial event where statisticians perform songs and skits about Bayesian probability theory.