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. Longer summary

Scott investigates the theory that public concern about rising crime is actually proxy concern about rising disorder (litter, graffiti, shoplifting, homelessness, tent encampments, boom boxes). He systematically examines data for each type of disorder and finds that most are either down from historical highs or only modestly increased from recent lows. Litter is down since the 1970s, graffiti is unclear but likely down in most places, shoplifting is up 20% from lows but still below 1990s levels, and homelessness is up 25% but equal to 1990s levels. He proposes four theories for why people perceive disorder as rising: the small 2020 bump, white people returning to cities through gentrification, romanticization of the unique 1930s-1960s crime minimum, and different forms of disorder in past versus present. Scott concludes by distinguishing between specific, evidence-based concerns about particular problems versus vague civilizational collapse narratives, arguing the former is both more accurate and more conducive to normal life. Shorter summary

Scott Alexander explores the difficulties in contextualizing statistics, providing numerous examples to show how the same data can be presented to seem significant or trivial. Longer summary

Scott Alexander discusses the challenges of putting statistical findings into context, showing how different comparisons can make the same statistic seem either significant or trivial. He provides numerous examples of effect sizes and correlations from various fields to illustrate this point. The post aims to promote awareness of how statistics can be manipulated and encourages readers to be vigilant when interpreting contextual comparisons. Scott also acknowledges the limitations of using standardized effect sizes but argues for their utility in certain situations where more specific measures are difficult to comprehend. Shorter summary

Scott Alexander warns about the potential misinterpretation of odds ratios in studies, explaining how to convert them to effect sizes for more accurate understanding. Longer summary

Scott Alexander discusses the potential for misinterpreting odds ratios in statistical studies, using a personal anecdote from a journal club. He explains how odds ratios can seem more significant than they actually are, and provides a method for converting them to effect sizes for better interpretation. The post includes a reference to Chen's study on interpreting odds ratios in epidemiological studies and gives an example of how a seemingly impressive odds ratio can translate to a more modest effect size. Scott emphasizes the importance of careful comparison between studies that report results using different metrics. Shorter summary

Scott Alexander explores how straight-line trends on graphs might mask the true impact of interventions, using examples like the Clean Air Act and Moore's Law to illustrate the complexity of interpreting such data. Longer summary

Scott Alexander discusses the difficulty of interpreting trend lines on graphs, particularly when evaluating the effectiveness of interventions or policies. He uses examples like the Clean Air Act, OSHA's impact on workplace safety, and Moore's Law to illustrate how straight-line trends can persist despite significant interventions or technological advancements. The post suggests that these trends might be maintained by control systems, where various factors adjust to keep the trend consistent. This perspective complicates the assessment of policy effectiveness and technological impact, as their effects might be visible in other areas rather than directly on the graph. The author expresses uncertainty about how to distinguish between scenarios where interventions truly don't matter and those where they're part of a complex control system. Shorter summary

Scott Alexander summarizes and analyzes various critiques of Thomas Piketty's 'Capital in the Twenty-First Century', finding that many of Piketty's key claims don't hold up well under scrutiny. Longer summary

This post summarizes various critiques and discussions of Thomas Piketty's book 'Capital in the Twenty-First Century'. Key points include: Matt Rognlie's criticism that Piketty didn't correctly account for capital depreciation, and that recent capital-share growth comes primarily from housing. The post questions Piketty's claim about higher returns for the super-rich, with various commenters providing insights on investment strategies and market behavior. It also discusses critiques of Piketty's income distribution statistics and data interpretation. The post concludes that many of Piketty's main claims, such as the rising rentier class and much better returns for the super-rich, don't hold up well under scrutiny, though some of his rules of thumb for growth are more robust than expected. Shorter summary

Scott Alexander reviews and responds to comments on his survey about sexual harassment rates in different fields, addressing methodological issues and presenting additional demographic data. Longer summary

This post discusses comments and analyses related to the SSC Survey Results on Sexual Harassment Levels By Field. It covers various points raised by commenters, including attempts to reproduce the results, alternative interpretations of the data, methodological critiques, and additional factors that might influence harassment rates. The post also presents additional data on harassment rates by various demographic factors, while cautioning against drawing strong conclusions without proper statistical analysis. Shorter summary

Scott Alexander cautions against drawing strong conclusions from regional scatterplots, demonstrating how apparent correlations can be artifacts of regional clustering rather than true relationships. Longer summary

Scott Alexander warns about the potential misinterpretation of regional scatterplots, using an example of a seemingly strong correlation between rainfall and gender balance in US states. He explains that such correlations can be misleading due to regional clustering, where the relationship appears strong between clusters but may not exist within them. The post discusses how this issue affects interpretation of data in various fields, including gun violence, national happiness, and income correlations. Scott emphasizes the importance of careful analysis and consideration of confounding factors when drawing conclusions from such plots. Shorter summary

Scott Alexander examines how different statistical presentations of the same data in social science studies can lead to vastly different interpretations, potentially misleading readers. Longer summary

Scott Alexander discusses the importance of understanding and interpreting statistical measures in social science studies, particularly focusing on correlation, percent variance explained, and visual representations of data. He examines two studies: one on IQ and state wealth, and another on wealth inheritance. Alexander highlights how different presentations of the same data can lead to vastly different interpretations, potentially misleading readers. He emphasizes the need for a good grasp of statistical concepts and realistic expectations when evaluating social science research, noting that correlations above 0.4 are rare in this field. Shorter summary

Scott Alexander explores how summary statistics can be misleading when describing relationships between variables, using examples of IQ's correlation with crime and income. Longer summary

Scott Alexander discusses two examples where summary statistics can be misleading. The first example involves the relationship between IQ and crime, where a large difference in average IQ between offenders and non-offenders coexists with a low correlation coefficient. The second example concerns the relationship between IQ and income, where substantial differences in average income across IQ deciles coexist with a relatively low correlation coefficient. In both cases, Scott emphasizes the importance of looking beyond summary statistics and considering the full distribution of data, potentially by examining scatter plots. Shorter summary

Scott Alexander analyzes online drug ratings, finding patients prefer older antidepressants while doctors prefer newer ones, and explores potential explanations for this paradox. Longer summary

Scott Alexander analyzes patient ratings of antidepressants from online databases, finding that older drugs like MAOIs are rated higher than newer ones. He then compares this to doctor ratings, discovering a negative correlation between patient and doctor preferences. The post explores possible explanations for these paradoxical results, including confounding factors and the hypothesis that newer antidepressants may actually be less effective. Scott extends the analysis to other drug classes, finding the negative doctor-patient correlation holds broadly, while the preference for older drugs is specific to psychiatric medications. Shorter summary

Scott Alexander explores the concept of 'Lizardman's Constant' and its implications for interpreting poll results, especially those concerning unpopular beliefs. Longer summary

Scott Alexander discusses the concept of 'Lizardman's Constant', which refers to the roughly 4% of respondents in polls who give outlandish or deliberately false answers. He explores this through three examples: a personal experience with survey responses, a poll about conspiracy theories, and a controversial study on climate change skepticism. The post argues that when dealing with unpopular beliefs, polls can only provide weak signals that are easily overwhelmed by noise from various sources, including jokesters, cognitive biases, and deliberate misbehavior. Scott concludes that polls relying on detecting very weak signals should be treated with skepticism. Shorter summary

Scott Alexander debunks a viral image about minimum wage and apartment affordability, showing how its methodology is flawed and recalculating more realistic figures. Longer summary

Scott Alexander critiques a viral image claiming to show the number of hours needed to work at minimum wage to afford a two-bedroom apartment in different states. He points out several flaws in the image's methodology and interpretation, including that it's not actually about minimum wage, that raising minimum wage wouldn't solve the problem, and that the numbers are misleading. Scott then recalculates the figures using more realistic assumptions, showing that the actual hours needed are much lower than the image suggests. He concludes that while minimum wage earners do face challenges, this particular image is not an accurate representation of those challenges. Shorter summary