Team Lead @webwith_Wendy

$oftware Dev | Debugging Specialist | Proudly American 🇺🇸 | True✨•₿Tech• Tech Solves localhost.com localhost Joined May 2022

Tweets

696
Followers

759
Following

818
Likes

7K

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

When colleagues ask me what I'm working on now, I mutter about "scientific workflow". Good scientific projects are entangled networks of assumptions and models and measurements in which the logic of each connection is transparent and can be checked. Working on 2 books and an ERC.

3 5 152 8K 37

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

Here's a paper with a skeleton of the idea, but there is really lots of research to do on the structure of workflow networks, now to make them robust, how to development diagnostics and calculi for steps within them. doi.org/10.1073/pnas.2…

1 5 35 2K 26

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

everyone stop fighting and touch the fluffy belly (beware)

0 1 31 2K 3

Download Image

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

How can we reform science? I have some ideas. But I am not sure you’ll like them, because they don’t promise much. elevanth.org/blog/2025/07/0…

5 60 185 34K 135

Elisabeth Bik @MicrobiomDigest

2 months ago

Good morning from London, where we start Day 2 of the @royalsociety meeting "The Future of Scientific Publishing". Yesterday, we discussed the problems; today, we're going to solve them all! #FutureSciPub

9 25 182 15K 9

Download Image

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

I haven't read this book, but the authors (Grant & Di Tanna) know their stuff, and they provide code for every script/engine. Meta- and mega-analysis one of those places where Bayes is natural and often easier than non-Bayes.

Stan @mcmc_stan

2 months ago

0 21 63 22K 42

4 50 306 19K 253

Download Image

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

I updated this post with links at bottom that go into more depth on mechanistic and philosophical reasons for troubles in science reform

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

I updated this post with links at bottom that go into more depth on mechanistic and philosophical reasons for troubles in science reform

5 60 185 34K 135

1 10 44 6K 20

Lior Pachter @lpachter

2 months ago

This is a good article and I agree with its argument for comprehensible research.

Richard McElreath 🐈‍⬛ @rlmcelreath

2 months ago

This is a good article and I agree with its argument for comprehensible research.

5 60 185 34K 135

0 8 24 10K 12

Richard McElreath 🐈‍⬛ @rlmcelreath

3 weeks ago

I have an old blog post series that discusses these approaches and shows the Bayesian approach in part 3: elevanth.org/blog/2021/06/2…

0 5 27 2K 10

Richard McElreath 🐈‍⬛ @rlmcelreath

3 weeks ago

There are multiple ways to estimate that ratio, and you should be careful about how you do it! 2-Stage-Least-Squares is popular, but it has poor variance, because estimating a ratio is one of the harder things to do robustly. I prefer a Bayesian approach, unsurprisingly.

1 3 13 2K 4

Richard McElreath 🐈‍⬛ @rlmcelreath

3 weeks ago

In my dept today we discussed deriving estimators from causal models. This can be opaque, but as a simple e.g. instrumental variable Z for estimating X on Y. Z –a–> X –b–> Y, and X <– U –> Y, where U is unmeasured, a and b are path coefs. We want to know b. How? >>

1 14 89 8K 61

Richard McElreath 🐈‍⬛ @rlmcelreath

3 years ago

Synchronized behavior without intelligent central control is common in nature. And it's something we actually understand for a change. @ncasenmare made this firefly simulator that explains the basics. Based on an example from @stevenstrogatz book "Sync". ncase.me/fireflies/

4 38 202 0 34

Download Video

Richard McElreath 🐈‍⬛ @rlmcelreath

4 days ago

I realize the world is burning, but here is the abstract of a talk I will give multiple times in different formats this month. With the feedback, I hope to write up something substantial on the theme in the remainder of the year.

6 28 264 11K 53

Download Image

Yan Holtz @R_Graph_Gallery

6 months ago

How to build a choropleth map with Python? 🐍 It's always the same steps: 1️⃣ Find a GeoJSON A GeoJSON file stores region boundaries. You can find plenty of free ones online. 2️⃣ Load it with GeoPandas Just one line of code, and you're ready to go! 🧵

4 68 363 18K 215

Download Gif

Yan Holtz @R_Graph_Gallery

6 months ago

Many ppl ask me why I compete with Coursera, Datacamp, Udemy.. But I create very different content! 🎮 Highly interactive 📈 Learn #dataviz AND #coding. Not just one. 👷‍♂️ Practice for real (like a lot!!) ⛏️ In depth: understand matplotlib for REAL matplotlib-journey.com

0 1 20 2K 5

Download Video

Yan Holtz @R_Graph_Gallery

6 months ago

Want to make better charts at work? Only 1 way: 🙇‍♀️ Practice 🤝 Get feedback ♻️ Repeat! The charts below are a glimpse of what students created in Matplotlib-Journey.com. They use the course Discord to share, get feedback, and refine their code! Only 2 days left to join🚀

0 12 131 7K 68

Download Image

Yan Holtz @R_Graph_Gallery

6 months ago

⏰ Last call! If you want to create stunning charts with Python, there are a 8 hours left only to join Matplotlib Journey! matplotlib-journey.com Thanks so much to the 414 people who joined already! 🙏 Graph by the awesome @CedScherer, python repro by @joseph_barbier

0 3 25 3K 11

Yan Holtz @R_Graph_Gallery

6 months ago

🔥 New Python library for #dataviz! "morethemes" gives your graph a better theme in 1 line of code! It currently offers 10 themes inspired by famous journals such as The Wall Street Journal, andThe Economist. Learn more: lnkd.in/eh5WGt7g Congrats @joseph_barbier !

2 45 267 11K 146

Download Image

Yan Holtz @R_Graph_Gallery

6 months ago

🍾 Yay! Excited to release a new project! It's a visual exploration of our aging world. It made it to the long list for the Information Is Beautiful Awards! 🚀 Tech stack: React + D3.js, of course ❤️ react-graph-gallery.com/example/popula…

0 2 26 1K 18

Download Video

Yan Holtz @R_Graph_Gallery

6 months ago

It's now incredibly easy to build calendar heatmaps! Thanks @joseph_barbier for your dayplot library! Documentation: josephbarbierdarnal.github.io/dayplot/tuto/a… If you like making charts with Python, come learn with us at matplotlib-journey.com!