Random thoughts about confidence intervals: When we teach precision & accuracy, we often use images of a target, like these from the Wikipedia article: en.m.wikipedia.org/wiki/Accuracy_… But I think this analogy leads to confusion about the interpretation of the confidence interval. 1/4

#EEG has come so far in the last century! Check out the Elektro-Encephalograph KDMRS 1, one of the oldest #EEG devices still around. Our Manfred Jaschke shares his knowledge of this antique during a recent visit to the Deutsches Museum. #100yearsEEG #CenturyofEEG #100yearsofEEG

Researchers have observed a Sumatran #orangutan in the wild repeatedly treating its own wound with a plant with several known medicinal properties - the first scientific record of this behaviour in a wild animal mpg.de/21886982/0429-… Dr. Isabelle Laumer caroline

Counterpoint: Obsession with "novelty" instead of ensuring a finding holds under different circumstances and contexts results in entire areas of research that are built on castles of sand.

38 years ago a woman in Coventry sent a letter to some scientists. That letter went on to be the most important in Alzheimer's research. Last year, I met Carol Jennings, who wrote it. 1/ thetimes.co.uk/article/e78c47…

Here's a cheat sheet for knowing what words to go along with different "probablies" ...

As you watch the Aurora this evening, it’s worth reflecting that you’re getting a rare direct glimpse of the power of Nature. Those charged particles causing the atmosphere to glow came from a sunspot complex 17 times the diameter of Earth and traveled across 90 million miles at

Here's a not-so-controversial one (1) Histograms are vastly under-valued as a tool for data analysis (2) Histograms are a critical concept to understand more advanced abstract ideas Thus, histograms should be taught carefully, early, and often a PhD methods sequence

I love this paper #psychstats

"Making Slides" Good advice on making slides (and talks more generally) from Kieran Healy. kieranhealy.org/blog/archives/…

96% of published findings in psychology are statistically significant. There are 2 options. 1) We study effects with more than 90% power, and more than 90% probability of being true. 2) There is MASSIVE publication bias. Hint: the answer is 2 journals.sagepub.com/doi/10.1177/25…

𝗖𝗮𝘂𝘀𝗮𝘁𝗶𝗼𝗻 𝗶𝗻 𝗻𝗲𝘂𝗿𝗼𝘀𝗰𝗶𝗲𝗻𝗰𝗲 Have we been thinking too narrowly? "Beyond mechanism – extending our concepts of causation in neuroscience" Imo quite an important paper by Mitchell and Potter calling for much broader view of causation. osf.io/63qvy/download

"The general rule is that people .... do not read." Hilarious, true, sad and reminds me of this bit from 2nd ed of Collins & Pinch where they quote a physicist talking about the fact that physicists don't read:

A model that honestly says it doesn’t know what will happen is not necessarily a bad model. Even with all the data, many things are hard to predict. We have to stop believing data is enough.

This last chapter "Horoscopes" is only 3 pages but I keep thinking it should be at the start of the book, because it is about scientific and social context of statistics. Anyway here it is:

Scientists when asked for their data "upon reasonable request"

WHAT IS HAPPENING TO THE FREQUENTISTS

Point-and-click stat software has been criticized since the emergence of personal computers. (DeGroot & Lehmann 1986)