A thread through the archive
Essays tagged “statistical analysis”. Follow an idea across the archive.
Scott analyzes whether AI forecasters will plateau near human levels or keep improving, arguing that even non-miraculous progress could yield 4-12 percentage point improvements in prediction market accuracy.
A replication of a 2023 neuroscience study on brain entrainment and learning found that the original effect likely doesn't exist, revealing how the study obscured key issues through statistical averaging and highlighting how AI tools are democratizing scientific scrutiny.
Scott examines whether reported increases in "crime" actually reflect concerns about "disorder" (litter, graffiti, shoplifting, homelessness, tent encampments), finding that most disorder metrics are either stable or down from historical highs, contradicting narratives of societal collapse.
Scott Alexander summarizes comments on his healthcare effectiveness debate with Robin Hanson, including clarifications, study author responses, and reader perspectives on various healthcare topics.
Scott Alexander explores correlations between PMS symptoms and various beliefs and traits, finding significant connections that leave him puzzled.
Scott Alexander challenges Robin Hanson's claim that medicine doesn't work by analyzing health insurance studies and presenting evidence of medicine's effectiveness.
Scott Alexander investigates why self-reported IQ scores in online surveys are implausibly high, identifying issues with conversion tools, reporting bias, and unreliable tests.
A critical review of 'Why Nations Fail' that examines the authors' academic work and methodology, while questioning the book's quality and practical implications.
The post challenges the notion that effect sizes below 0.50 for medications are clinically insignificant, using antidepressants as a case study and comparing them to other common drugs.
Scott fact-checks and disproves a claim that all healthy people have mystical experiences using SSC Survey data.
Scott Alexander investigates the reliability of dietary supplements, finding that while issues exist, most are not completely fake as some media reports claim.
Scott Alexander examines the poor quality of research on homework effectiveness, finding only one well-designed study showing positive effects for high school algebra.
Scott Alexander shares 34 diverse and interesting links on topics ranging from historical curiosities to current scientific debates, with brief commentaries on each.
Scott Alexander responds to comments on his ivermectin article, discussing criticisms, the worms hypothesis, vaccine skepticism, and journalism quality.
Scott summarizes reader comments on his 'Secrets of the Great Families' post, covering additional examples, statistical discussions, and personal perspectives on family achievement.
Scott examines data on COVID-19 lockdown effectiveness, finding they likely reduced transmission but at significant costs, with targeted measures being most effective.
Scott Alexander directs readers to his essay on Works in Progress examining why suicide rates didn't increase during the COVID-19 pandemic as expected.
Scott Alexander analyzes a study suggesting cloth masks may be harmful, but remains cautiously in favor of their use despite the uncertainty.
Scott Alexander reviews John Gottman's marriage counseling methods, finding them intuitively appealing but scientifically questionable.
The post critically examines the impact of India's 1991 economic reforms, suggesting that the country's economic growth began earlier and that the causes are more complex than commonly believed.
Scott Alexander attempts to replicate a study linking beef jerky consumption to manic episodes in bipolar disorder, finding no significant relationship in his analysis of SSC survey data.
Scott Alexander critiques a misreported study on trigger warnings, highlighting its flaws and limited relevance to the broader debate on their use in colleges.
Scott Alexander examines conflicting narratives about cancer treatment progress, analyzing data to show that while some improvements are due to social factors, there's evidence of genuine advancements in cancer treatment and outcomes.
Scott Alexander explores why US suicide rates aren't higher despite high gun ownership, concluding that the US likely has a low base rate elevated by gun availability.
Scott Alexander critically examines a major meta-analysis on antidepressant efficacy, noting potential biases and comparing its surprising drug rankings to his own previous analysis.