The hottest Statistics Substack posts right now

And their main takeaways
Category
Top Technology Topics
No Grass in the Clouds 99 implied HN points 04 Oct 24
  1. Rodri is a key player for Manchester City, showing impressive skills in tackles, passes, and goals. He's unique in the modern game.
  2. There are rankings for the best American and Premier League soccer players, showcasing talent from different leagues.
  3. There's buzz around players like Erling Haaland potentially reaching high goal tallies in a season, while other players are gaining attention for their performances.
Data Science Weekly Newsletter 179 implied HN points 29 Aug 24
  1. Distributed systems are changing a lot. This affects how we operate and program these systems, making them more secure and easier to manage.
  2. Statistics are really important in everyday life, even if we don't see it. Talks this year aim to inspire students to understand and appreciate statistics better.
  3. Understanding how AI models work internally is a growing field. Many AI systems are complex, and researchers want to learn how they make decisions and produce outputs.
The Intrinsic Perspective 9701 implied HN points 30 Jan 25
  1. Life has ups and downs, and problems often come in clusters. It's normal to feel overwhelmed when things go wrong.
  2. When you're at a low point, remember that life is like a rollercoaster with many twists and turns. Things often improve after tough times.
  3. Statistically, when you feel at your worst, it might actually be the moment before things start to get better. Hang in there!
Cremieux Recueil 434 implied HN points 27 Dec 25
  1. Make sure your criticism is correct: check the data, run the needed analyses, and only accuse or declare problems when you can justify them.
  2. Focus on meaningful, relevant issues that actually change conclusions — don’t list hypotheticals; quantify or demonstrate how a confound or error would affect the results.
  3. Be generous and contextual: assume good faith, ask for clarification or contact authors privately when fixable, and build enough domain knowledge to notice real problems instead of relying on rote one‑liners.
The Infinitesimal 499 implied HN points 05 Jul 24
  1. Human traits are influenced by many tiny genetic factors, making understanding them complex. This means small changes in genetics can impact our traits in different ways.
  2. Talking about nature versus nurture isn't simple; both genetics and environment play big roles. There's often a mix of many genes working together rather than clear-cut definitions.
  3. The concept of heritability is tricky and often debated. Different studies can show very different results about how much genetics affect things like intelligence or behavior.
Get a weekly roundup of the best Substack posts, by hacker news affinity:
The Infinitesimal 339 implied HN points 23 Jul 24
  1. Assortative mating happens when partners select each other based on certain traits, like height or education, making their children more genetically similar over generations.
  2. This type of mating can lead to increased genetic variance in the population, but does not change the genetic variance within families because the parent's traits balance out among the children.
  3. When estimating heritability or variance, it’s important to use the right approach. Population-level estimates can be misleading if based on family data, and vice versa.
Data Science Weekly Newsletter 219 implied HN points 08 Aug 24
  1. Camera calibration is crucial in sports analysis. It helps track players' movements accurately by mapping video frame positions to real field locations.
  2. Understanding the context of data is important for responsible data work. Datasets need good documentation and stories to highlight their historical and social backgrounds.
  3. There's a new, free encyclopedia for learning about cognitive science. It offers easy-to-read articles on various topics for students and researchers.
Cremieux Recueil 477 implied HN points 17 Dec 25
  1. When you add up many positively correlated variables with positive weights, different composite scores tend to become very similar because shared covariance grows faster than unique variance, so the sums converge toward perfect correlation as components increase.
  2. GDP will naturally correlate highly with lots of other measures since it aggregates overlapping components (and is sometimes included in other indexes), and aggregation reduces within-group noise which mechanically inflates between-group correlations.
  3. Adding items to make a composite more reliable often makes it harder to distinguish from other composites, so improving reliability can reduce discriminant validity (for example, measures like grit can converge with conscientiousness).
JoeBlogs 2889 implied HN points 10 Jan 24
  1. Four players have a reasonable shot at the Baseball Hall of Fame this year.
  2. Adrián Beltré is expected to get in with a high percentage.
  3. Todd Helton, Joe Mauer, and Billy Wagner are also strong contenders for the Hall of Fame.
Freddie deBoer 5321 implied HN points 10 Feb 25
  1. Patrick Mahomes has had a noticeable decline in his performance over the last two seasons, which is surprising for someone viewed as one of the best quarterbacks. People should be allowed to discuss this drop in stats and performance even if his team continues to win.
  2. Despite still being a good quarterback, his recent numbers do not match the elite standards he set earlier in his career, which raises questions about his current ability. His style of play has shifted from aggressive to more conservative, leading to fewer big plays.
  3. Sports media often avoids criticizing star players like Mahomes due to their past success and the team's winning record. However, if other quarterbacks experienced similar declines, they would likely face significant scrutiny, suggesting that it's time for a more honest conversation about Mahomes.
Wyclif's Dust 2146 implied HN points 12 Jul 25
  1. Effect sizes matter when they're measured on scales that are important to real life. For example, a small change in the chance of going to university can have a huge impact on families and policies.
  2. Correlation coefficients aren't the only way to measure effect sizes. Sometimes, using different scales can make it clearer how significant an effect really is.
  3. Noisy outcomes can still be meaningful. Just because there's variation around a mean doesn't mean the underlying effect isn't strong; it's important to look at how much outcomes change in significant ways.
JoeBlogs 2044 implied HN points 02 Feb 24
  1. The game 'Choose the Hall of Famer' challenges perceptions about player value based on stats and accomplishments.
  2. Comparison between players like Jim Plunkett and Joe Namath shows that stats alone may not dictate Hall of Fame worthiness.
  3. Analyzing players like Scott Rolen and Jim Edmonds reveals how defensive contributions can impact Hall of Fame considerations.
Freddie deBoer 2165 implied HN points 03 Jul 25
  1. Regression to the mean means that extreme results are unlikely to happen again without some change in conditions. If a team's situation changes, it’s not just luck but a new factor affecting performance.
  2. Using regression to the mean incorrectly can lead to confusion. If someone thinks a team will do worse because they lost players, that’s not regression to the mean; it’s a different kind of prediction.
  3. There’s a risk of making mistakes by assuming past results will always influence future ones, like betting based on past game outcomes. Each situation should be treated by its own conditions.
The Shores of Academia 39 implied HN points 03 Oct 24
  1. Flawed meta-analysis can mix different studies that aren't similar, making it hard to draw clear conclusions about their effects on things like mental health.
  2. It’s important for researchers to look at specific impacts and not just assume that a random-effects model explains everything. Understanding the differences in outcomes can lead to better insights.
  3. Proper analysis in studies is really important, especially when people's health is at risk. Ignoring negative findings can mislead people about the safety of products like drugs.
Unsafe Science 79 implied HN points 02 Feb 26
  1. Many microaggression studies rely on correlational, nonexperimental data but still claim causal relationships between racism, microaggressions, and outcomes.
  2. Concluding that microaggressions cause negative health or mental-health impacts from simple correlations is not justified without stronger causal evidence.
  3. Peer review has often failed to catch these methodological flaws, allowing unsupported causal claims to persist in the literature.
Cremieux Recueil 507 implied HN points 13 Nov 25
  1. Trends can look similar, but the reasons behind them can be very different. Just because two places produce more strawberries doesn't mean they do it the same way.
  2. Measurement invariance is important. This concept means you can’t just compare numbers across different times or places without understanding how they were measured.
  3. Not all trends matter equally. Sometimes the reasons behind the changes are significant, and other times they might not be. It's essential to dig deeper to understand what the numbers really mean.
In My Tribe 288 implied HN points 07 Dec 25
  1. Certain personality traits like being assertive and energetic can lead to higher earnings, while traits like being anxious or preferring routine work are linked to lower earnings.
  2. A small correlation in data, such as between social media use and depression, can significantly impact outcomes, but it's important to analyze data correctly and not rely solely on models.
  3. Current fertility rates among older Millennials appear similar to older generations, but the context matters; using outdated comparisons can be misleading, and true trends show a decline in fertility.
Silver Bulletin 364 implied HN points 02 Dec 25
  1. The QBERT system ranks NFL quarterbacks based on many performance factors, not just traditional stats. It looks at things like rushing yards and how well they handle pressure.
  2. Ratings are adjusted for different conditions, like the strength of the opposing team and the weather, making it fairer across the board.
  3. Along with current ratings, QBERT provides future projections for quarterbacks, taking into account their recent performances, age, and experience.
David Friedman’s Substack 260 implied HN points 20 Dec 25
  1. Total fertility rate (TFR) is a snapshot-based prediction that can underestimate the number of children women will actually have if they postpone births, while completed fertility rate (CFR) is what determines population change.
  2. There is a biological limit to how late people can have children, so shifting births to older ages can only go so far, though advances in reproductive technology could change that limit.
  3. Life expectancy at birth (an estimated measure) is also a prophecy and can fall during temporary mortality shocks even though completed life expectancy will likely be higher if mortality rates continue to decline.
Freddie deBoer 1206 implied HN points 27 Jul 25
  1. Justin Fields might not be a good quarterback after evaluating his performance over 50 games. Many fans still hold hope for him because of his past potential.
  2. Fields has struggled with passing yards, averaging only 155.6 yards per game, which is quite low for an NFL starter. Elite quarterbacks usually get much more yards in fewer games.
  3. Even with his talent, Fields' inefficiency in throwing the ball makes it hard for his team to be competitive in a league that relies heavily on passing.
rachaelmeager 535 implied HN points 04 Jun 24
  1. The Polya urn model, though simple at first glance, reveals the complexity of statistics and emphasizes the importance of understanding problems deeply before attempting to solve them.
  2. Teaching and learning in math are not just about facts; they require creativity and passion to engage students, much like how poets perceive deeper meanings in their art.
  3. There is a strong connection between the arts and sciences, where both disciplines can benefit from understanding each other, and students should learn foundational concepts in both to grasp the complexities of the world.
Mindful Modeler 419 implied HN points 28 May 24
  1. Statistical modeling involves modeling distributions and assuming relationships between features and the target with a few interpretable parameters.
  2. Distributions shape the hypothesis space by restricting the range of models compatible with specific distributions like a zero-inflated Poisson distribution.
  3. Parameterization in statistical modeling simplifies estimation, interpretation, and inference of model parameters by making them more interpretable and allowing for confidence intervals.
Admired Leadership Field Notes 1022 implied HN points 11 Feb 24
  1. Momentum in sports can lead to a shift in energy and positivity, affecting the outcome of a game.
  2. Even though statistical experts claim momentum is not real and linked to the gambler's fallacy, it is a common occurrence in sports that can impact a team's performance.
  3. Teams that effectively harness momentum by maintaining a streak of positive outcomes have a higher probability of winning, as seen in data analysis of NFL games.
The Counterfactual 199 implied HN points 27 Jun 24
  1. Always look at the whole distribution of data, not just the average. The average can be affected by extreme values, so it's crucial to see the bigger picture to understand what the data really tells us.
  2. Consider the baseline or reference point when evaluating numbers. Knowing how a number compares to others helps us understand if it's large or small, which gives us better context.
  3. Understand the story behind the data-generating process. This means recognizing the factors that led to the results we see, which helps in identifying possible biases or alternative explanations.
Holodoxa 239 implied HN points 14 Jun 24
  1. Bayes' Theorem is a powerful concept in probability theory that helps update beliefs based on new evidence, highlighting the importance of combining prior knowledge and new data.
  2. Bayesian methods can offer valuable improvements to scientific research practices by emphasizing uncertainty, effect magnitude, and probability distributions over traditional p-values and null hypothesis testing.
  3. The concept of the brain functioning as a prediction machine aligns with Bayesian principles, suggesting that the brain uses prior knowledge and new sensory inputs to make predictions and construct conscious experiences.
Silver Bulletin 243 implied HN points 21 Nov 25
  1. The Houston Rockets are playing an exciting, unconventional style of basketball, featuring a young team that is currently one of the best in the league. Their success is partly due to smart team-building and embracing unique strategies, like focusing on offensive rebounds.
  2. Players like Alperen Şengün and Amen Thompson are showing impressive growth, helping the team perform well. Thompson's athleticism and ability to score create opportunities, while Şengün’s improved efficiency makes him a key player.
  3. Despite their strong start, there are questions about their long-term success, especially with injuries and how teams will adapt to their tactics. The Rockets' future looks bright, but they still need to figure out the best way to work together.
Cremieux Recueil 803 implied HN points 22 Jul 25
  1. Statistical controls aren’t a magic solution; using them incorrectly can lead to wrong conclusions. It's important to understand the underlying relationships between variables before just plugging numbers into an equation.
  2. Matching groups in studies to control for variables often isn't enough. You might still end up with biases if the controls aren’t comprehensive or well-measured.
  3. Over-controlling or trying to account for too many factors can confuse the results. Sometimes, less control can provide a clearer picture, just like how comparing fast food and fine dining should keep their unique qualities intact.
Reality's Last Stand 1474 implied HN points 27 Mar 23
  1. The Univariate Fallacy manipulates using single-variable focus to distort reality and push agendas.
  2. There are two versions: one exaggerates group differences, and the other minimizes them.
  3. This fallacy is used to justify false depictions of reality, especially regarding sex and gender.
Teaching computers how to talk 167 implied HN points 03 Dec 25
  1. Language models are just predictions and approximations of text, which means they can sometimes make up information that sounds believable but isn't true.
  2. These models don't understand the world the way humans do; they only see words related to other words, so they can get confused easily and not follow conversations well.
  3. People who develop language models try to make them safer, but sometimes these systems can be tricked, and that’s a serious concern since they can't truly differentiate between safe and dangerous content.
Mindful Modeler 778 implied HN points 16 Jan 24
  1. Quantile regression can be understood through the lens of loss optimization, specifically with the pinball loss function.
  2. In machine learning, quantile regression is essentially regression with the unique pinball loss function that emphasizes absolute differences between actual and predicted values.
  3. The asymmetry of the pinball loss function, controlled by the parameter tau, dictates how models should handle under- and over-predictions, making quantile regression a tool to optimize different quantiles of a distribution.
Chartbook 543 implied HN points 04 Aug 25
  1. Overcapacity in the diamond market is a key issue right now. This means there are more diamonds available than people want to buy.
  2. Statistical data is often lost or missing, which can lead to misunderstandings about various topics. It's important to question the numbers we see.
  3. There are interesting connections made between technology, like Samsung products, and philosophical ideas. It's fun to explore how different areas can relate to our lives.
Patterns in Humanity 1159 implied HN points 17 Feb 23
  1. First, there is a detailed analysis of the financial impact of immigration in Denmark based on a government report.
  2. Second, the analysis explores the rates of violent crime convictions by nation of origin, showing disparities between groups.
  3. Lastly, the importance of adjusting for age and sex in understanding the differences in financial contributions and crime rates among immigrants is highlighted.
Weight and Healthcare 738 implied HN points 27 Dec 23
  1. Using percentages without proper context can be misleading, it's crucial to provide a full picture for accurate interpretation.
  2. Understanding the difference between relative and absolute risk in statistics can prevent manipulation and provide a clearer view of the data.
  3. Different methods for handling dropouts in trials, like LOCF and BOCF, can impact outcomes significantly and need careful consideration in research.
Marc Stein 668 implied HN points 09 Jan 24
  1. Several NBA teams are performing historically poorly this season, being outscored by at least 10 points per game.
  2. Ja Morant's season-ending injury adds to the struggles faced by the Memphis Grizzlies, impacting their performance in the league.
  3. The list of NBA teams with significant negative point differentials this season is unprecedented, with four teams facing double-digit losing margins.
Marc Stein 589 implied HN points 24 Jan 24
  1. There has been only one in-season coaching change in the NBA so far this season.
  2. Joel Embiid of the Philadelphia 76ers has been scoring impressively with 1,156 points in 32 games.
  3. The Boston Celtics were the first team to reach 30 wins this season.
Marc Stein 589 implied HN points 17 Jan 24
  1. The NBA has been implementing two-game baseball series for scheduling efficiency.
  2. Historical data shows that splits are the most likely outcomes in these series.
  3. Home teams in the NBA have historically had an average winning percentage of .586.
Unsafe Science 116 implied HN points 28 Nov 25
  1. People are generally pretty accurate at judging others, and many stereotypes reflect real group differences; when people have individual information they rely on it much more than on stereotypes.
  2. Biases and self‑fulfilling prophecies do occur, but studies show their effects are typically small, fragile, and short‑lived, while the literature has often overstated their prevalence.
  3. Overemphasizing bias can lead to misguided policies and hurt the credibility of social science, so decisions should follow the full evidence and balance accuracy with non‑discrimination.