#Statistics

My longtime labmate-turned-student/friend1 Dhruva Karkada recently wrote a sick paper on data statistics which deservedly went viral on Twitter, in part beca...

Sadly, taking away valuable disclosure avoidance tools doesn't make fundamental trade-offs go away.

I applied a Bayesian hierarchical binomial model to ~800k MLB pitches (2020-2025) to assess whether Statcast's breaking ball taxonomy has discriminant validity. The short version: it doesn't, at least not between sliders and sweepers.…

I can’t seem to find a definitive answer to this. So, I thought I’d ask here. Is it ideal to include the elbow or not? I’m practicing some previous year question papers for an entrance exam and I came across this question: “If the plot shows a sharp drop…

[D] For example, American men are on average taller than Japanese men, so would American men on average have a larger standard deviation in height?…

I'm cold emailing professors with no success. I've stated that I would be willing to put in 10 hours a week to help aid in their research but is that not enough? Am I getting ghosted because they are looking for 20+ hours?…

Hi all! I'm working on my Bachelor thesis at the moment and I did a simple mediation analysis, however my total and direct effect are not significant but my indirect effect is. Can someone maybe explain what this means?…

AI Is Just Statistics T-Shirt A design for builders who know that underneath the hype,...

From Dev.to - ai: Why We Built a Trusted Statistics Hub for AI and Marketing (And Why Data Alone Isn't Enough)

Statistics are changing with the times, Stats NZ CEO Colin Lynch writes. As the government statistician, I’m responsible for the integrity of New...

Introducing Durjay Views — A Simple Laravel View Counter Package Tracking views in a Laravel...

The Bureau of Labor Statistics on Friday reported a better-than-expected jobs report for April. CBS News MoneyWatch correspondent Kelly O'Grady breaks down the numbers.

A precise, worked explanation of why paired bootstrap is the correct procedure for within-subject LLM evaluation designs, and why near-zero covariance between score vectors means it provides almost no practical benefit.

How big should an LLM eval set be? The power-math for binomial accuracy, sequential testing, and stratification, and why 100 examples is a coin flip.

Penn researchers have developed a smarter AI method for solving notoriously difficult inverse equations, which help scientists uncover hidden causes behind observable effects.…

Crime is down across New York City so far this year, with April setting records for the fewest violent crimes in NYPD history.

From Dev RSS Feed: Why Today's AI Skepticism Mirrors Yesterday's Distrust of Statistics

For decades, psychologists have debated whether the human mind can be explained by one unified theory or must be broken into separate parts like memory and attention.…

From Dev.to - database: GBase 8c Performance Tuning: From Statistics to Execution Plan Optimization