Daily data science tweets from @JohnDCook.
Houston
Joined November 2010
- Tweets11.7K
- Following19
- Followers195K
- Likes121
Pinned Tweet
“Statistics is hard, especially when effects are small and variable and measurements are noisy. There are no quick fixes … and a formulaic approach to statistics is a principal cause of the current replication crisis.” — Blakeley McShane
You can learn things from a dozen human subjects you couldn't learn from a million mice. Data relevance beats data size.
Data Science Fact retweeted
here's you regular reminder that carseats have probably saved very few lives in aggregate vs. general improvements in road and care safety
despite massive increases in carseats for 0 & 3 year olds since 1959, their mortality declines have been entirely typical
'A statistical analysis, properly conducted, is a delicate dissection of uncertainties, a surgery of suppositions.' -- M. J. Moroney
How to solve for parameters of beta distribution with given mean and variance johndcook.com/blog/2021/04/0…
The interplay of Bayesian and Frequentist analysis www2.stat.duke.edu/~berger/p… [pdf]
Nine great stats papers published after 1970 normaldeviate.wordpress.com/… chosen by Rob Tibshirani
Estimating the chances of something that hasn't happened yet johndcook.com/blog/2010/03/3…
Edward Tufte-style presentations in CSS github.com/edwardtufte/tufte… and LaTeX: tufte-latex.github.io/tufte-…
The Bayes estimator with minimum quadratic loss for a parameter is the posterior mean of that parameter.
'Choice of an appropriate family of distributions may be the most challenging phase of analysis.' -- David Cox
Why fitting a logistic is nearly impossible from early data
johndcook.com/blog/2026/09/1…