@ProbFact

Daily tweets on probability from @JohnDCook.

johndcook.com/blog/applied-probability/
Joined November 2009
  • Tweets9.4K
  • Following19
  • Followers147K
485Media
Putting probability to work johndcook.com/blog/applied-p…
8
30
3
106
A probability space is a measure space such that the measure of the whole space is 1.
4
29
2,735
'Probabilistic' comes from Latin. 'Stochastic' comes from Greek.
15
2
98
3,413
Explaining probability to a jury johndcook.com/blog/explainin…

Explaining probability to a jury | Expert witness

A panel of jurors is unlikely to contain many people who understand probability, but understanding probability may be critical to a fair trial.

johndcook.com
1
16
4,463
The problem w/ trying to achieve reliability w/ multiple software implementations: they're not independent.
1
16
4,294
A Short Introduction to Optimal Transport and Wasserstein Distance alexhwilliams.info/itsneuron…
2
39
4,708
Uniformity increases entropy johndcook.com/blog/2025/06/2…

Uniformity increases entropy

Entropy increases as system states become more uniform and decreases as they become further from uniform.

johndcook.com
2
1
27
4,224
A random number generator may have excellent statistical properties and yet be unsuited for cryptography.
1
5
48
5,067
Let τ be Kendall's tau and let ρ be Spearman's rho. Then -1 ≤ 3τ - 2ρ ≤ 1.
2
23
4,693
'All probabilities are conditional on something, and to be useful they must condition on the right thing.' -- Frank Harrell
7
1
94
4,899
Cosine power approximation to normal johndcook.com/blog/2020/07/2…

Cosine power approximation to normal

Cosine raised to a power makes a good approximation to a Gaussian probability density. The approximation improves as the power increases.

johndcook.com
13
4,125
The moment generating function of a random variable X is the two-sided Laplace transform of its density function f_X, with the sign of the argument flipped.
23
4,603
The Mellin transform of the product of two independent random variables is the product of their Mellin transforms.
1
21
4,606
Perfect and imperfect shuffles johndcook.com/blog/2026/01/0…

Perfect and imperfect shuffles

Shuffling a deck of cards works because ordinarily the process is imperfect. But with perfect shuffles, a deck will return to its original order.

johndcook.com
1
16
4,584
'There are only five probabilities the average human can handle: 99 percent, one percent, 100 percent, zero, and 50-50. That’s it.” — Richard Thaler
3
8
2
73
5,496
Coefficient of variation = standard deviation / mean
1
2
39
4,725
If A and B are independent causal factors leading to L, then L is called a collider. After conditioning on L, A and B are /not/ independent.
1
1
27
4,727
Counting selections with replacement johndcook.com/blog/select_wi…

Counting selections with replacement | Combinatorics

Calculating the number of possible selections with replacement from a set

johndcook.com
1
6
4,180
For a multivariate normal, the probability of being within two standard deviations of the mean goes to zero as the dimension increases.
5
28
4,755
Tweedie distributions en.wikipedia.org/wiki/Tweedi…

Tweedie distribution - Wikipedia

en.wikipedia.org
1
12
4,511
Logs, Tails, Long Tails moultano.wordpress.com/2013/…

Logs, Tails, Long Tails

Learn the shape of the logs of probability distributions, and you’ll be able to guess how they behave.

moultano.wordpress.com
2
20
4,218
Load more