“I’m way closer to LeBron James than you are to me.” -- Brian Scalabrine He's probably right, because in a lognormal distribution of ability, it's levels to this … www.allendowney.com/blog/2025/11...

The #Scicloj group is initiating a new study group: #DSP in #Clojure. We will follow @allendowney.bsky.social's #ThinkDSP book and practice it in Clojure. clojureverse.org/t/clojure-ds...

The newest chapter of Think Linear Algebra is up now! It is about least squares regression, QR decomposition, and orthogonality: allendowney.github.io/ThinkLinearA...

Five-year survival rates might be the most misleading statistics in medicine. Even smart people can make incorrect inferences. Here are the top four: 1. If a patient is diagnosed early, it is tempting to think the probability is 91% that they will survive five years after diagnosis.

The original sin of the engineering curriculum is the Foundation Fallacy: The assumption that math (especially calculus) and science (especially physics) are (1) the foundations of engineering, and therefore (2) the prerequisites of engineering education. www.allendowney.com/blog/2025/10...

I just posted a new chapter of Think Linear Algebra. It's about projection, rejection, rotation, and pool! allendowney.github.io/ThinkLinearA...

I love a good Simpson's paradox. Sadly, this is not one of them www.allendowney.com/blog/2025/10... In fact, I think the whole paper is nonsense. Published in Nature, too.

Sadly, my primary team (the Red Sox) and emergency backup team (the Padres) were both knocked out of the playoffs yesterday. Now I am left to cheer for my team of last resort (the Notyankees).

Sometimes we can use Bayesian methods to infer the effect of selection bias and produce an unbiased estimate. Here's an example that uses PyMC to solve a classic probability puzzle (the image shows what I think is the original version). www.allendowney.com/blog/2025/09...

At this point I'm just barely making enough $ on this cohort to cover the platform fees. It's going to run anyway but I'd really love to have a few more people signed up. Use the code SIXTY for 60% off at registration.

I have published five new chapters of Think Linear Algebra! Read about the project here allendowney.com/blog/2025/09... Or jump straight to the book allendowney.github.io/ThinkLinearA... And now… Asteroids!

On September 3 I'm giving a talk for the Boston Python User Group, called "A Future of Data Science" www.meetup.com/bostonpython... This is a talk from posit::conf last year, updated with new data and the experience of an interesting year.

Between 2021 and 2024, marijuana was legalized in eight states totaling 18% of the US population. During this time, adult use increased and youth use was unchanged. Data from NSDUH 2024.

As a graduate of an all-boys high school, I am very interested to see the results...

For anyone who likes LLMs and daytime game shows.

Some news articles suggest young men are conservative Republicans with sexist attitudes. But big picture, young men's views are pretty much on trend. Here's the data: allendowney.substack.com/p/are-young-...

We're kicking off this new workshop on August 5.

Everyone can do ML. Few can do Bayesian modeling. Set yourself apart with skills that drive deeper insight + better decisions. Join the next Applied Bayesian Modeling Workshop by PyMC Labs. Hands-on. Practical. Real-world. 📅 Limited seats → dub.link/bayes-workshop #PyMC

ChatGPT and I think that "AI tools are shifting the boundary of what’s viable, and that’s likely to increase the net demand for software development, not decrease it." More Viable Projects = More Things to Build chatgpt.com/share/686c2e...

Starting August 5, PyMC Labs is running a new workshop on Bayesian modeling in PyMC -- and I'm one of the instructors. If you want to get started with Bayesian stats, this is your chance! See below for details.

I love this -- possibly best ever.

At PyData Boston last night, I announced a new project: Think Linear Algebra! This blog post explains the idea, including a sample chapter and a terrible AI-generated cover. www.allendowney.com/blog/2025/05...

Can LLMs answer open-ended survey questions like real people? 🧠 @allendowney.bsky.social tested GPT-4, Claude & others on 2020 ANES data. Models matched the order of top concerns—but often cited issues (like inflation) that weren’t big then. Useful, but not time-aware. 👉 dub.link/synth-respon...

My Think Stats hard copy has arrived! Here's what's new in the third edition: allendowney.github.io/ThinkStats/c...

Time Series Analysis with StatsModels Video from my PyData Global tutorial is up now: www.youtube.com/watch?v=foMb...

Think Stats 3e is on its way to the printer! (And available to pre-order) Here's the new cover, with a suspicious-looking archerfish. Blog post with the details: www.allendowney.com/blog/2025/04...

How close are LLMs to modeling real human behavior? We tested GPT-4o, Claude 3, Gemini, and others on actual survey data (GSS-style). Some were shockingly human-like, others flopped 📊 Full results + methods → dub.link/synth-consum... 🤝 Exploring synthetic consumers? Let’s chat: [email protected]

At PyMC Labs I've been working with a group developing synthetic consumers for marketing research. We just published this white paper with an overview of work in this space -- and we have a blog post coming next week with some experimental results. www.pymc-labs.com/blog-posts/s...

People born in the 1990s and 2000s have fewer children than previous generations at the same ages -- new data from NSFG. If circumstances prevent them from having the children they want, these trends might change. But it looks like they just want fewer. www.allendowney.com/blog/2025/03...

This Upshot article is very good -- and it cites a related article I worked on: aibm.org/commentary/n...

The schedule for PyCon US 2025 is live! On May 15, I'm offering a new tutorial called "Analyzing Survey Data with Pandas and StatsModels". We'll explore data from the General Social Survey, run regression models, and visualize results. us.pycon.org/2025/schedul...

Check out these blog posts from users showing how they work with our new data download API in Python and R: @allendowney.bsky.social, Python: www.allendowney.com/blog/2024/11... kjytay, R: www.r-bloggers.com/2025/01/down... Let us know how you're using the features & how we could improve them!

New bird on my feeder this morning. I think it's a ruby-crowned kinglet, but maybe @jerthorp.bsky.social can confirm or deny.

Unmarried Dads matter too open.substack.com/pub/ofboysan...

⚖️ Bayesian methods give us a robust way to measure uncertainty 👀 By integrating them with genAI, we are building systems that go beyond simple predictions 🔔Stay tuned for deep-dives on Bayesian agents, causal AI & sound synthetic data: pymc-labs.com/newsletter #generativeai #airesearch #bayesian

New German translation of Think Python 3rd edition!

I have published three new videos where I work through Chapter 2 of Think Python: www.youtube.com/playlist?lis...

Interesting report from AIBM. Boys and girls do about equally well on the SAT (with more boys in the tails), but girls are way ahead on high school GPA. ofboysandmen.substack.com/p/the-high-s...

Confidence in the press has been declining since the 1970s. The trend might have reversed among liberals, so polarization has increased. open.substack.com/pub/allendow...

Recently I posted NSFG data showing marriage patterns for young women in the U.S. compared to previous generations. The percentage of women married before age 24 has dropped to about 10%. Now here's the same analysis for young men. The pattern is similar -- very few young men are getting married.

Here's what I wrote about LLM-assisted programming when I started using ChatGPT in 2023. www.allendowney.com/blog/2023/04... I think it holds up, but there are a couple of places where you can hear the quotation marks on "laser beams".

Pandas people: Should you forget about crosstab and pivot_table, and use groupby for everything? I'm unsure, but I share some thoughts at the end of this post: www.allendowney.com/blog/2024/12...

Grammar take: If "drive drunk" means driving while being drunk, "drive safe" means driving while being safe, so it's grammatically correct, meaningful, and actually better than driving safely. "Drive safely" is imperative, "drive safe" is optative.

Young Americans are marrying later, and it looks like more of them will remain unmarried Updated with new data from the National Survey of Family Growth

@bsky.app Why am I getting black boxes when I try to upload a photo? The preview looks fine and then when I post... black box.

How does income vary with education and age? Another excerpt from Elements of Data Science, Multiple Regression with StatModels allendowney.substack.com/p/multiple-r...

Talks at Google Year in Review. There I am at t=84 youtu.be/jYXHAJnLvEs?...

I'm presenting a workshop on Time Series Analysis at PyData Global, Thursday at 13:00 UTC global2024.pydata.org/cfp/talk/KLX... Good virtual seats still available!

Tan H. Nguyen has translated Think Python 3e into Vietnamese! bitbucket.org/tanhuynhng/t... And he has posted a video of Chapter 1 here www.youtube.com/watch?v=OEcb...

Boycott Thanksgiving by reading this totally unrelated new blog post: www.allendowney.com/blog/2024/11...