Data Science Fact

“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

The Kolmogorov-Smirnov test is often used to test goodness of fit.

The mean of the mean is the mean. johndcook.com/blog/2014/04/0…

There's a lot to think about in this slide from Frank Harrell's presentation, linked to yesterday.

"When you hear hoofbeats in Texas, think horses, not zebras." -- Med school aphorism Also Bayesian statistics.

Implications of the Draft FDA Bayesian Guidance fharrell.com/talk/bguide/

What every statistician should know about cross-validation robjhyndman.com/hyndsight/cros…

'Random error is but 1 of 20 threats to learning from data. It receives disproportionate attention because it is only threat math-modeled.' @EdwardTufte

If you like @DataSciFact you might like @SciPyTip.

Keeping data and code together with org-mode johndcook.com/blog/2022/08/1…

There are more things in heaven and earth, Horatio, than are dreamt of in your statistical model. -- Shakespeare

Rao-Blackwell: Conditioning on a sufficient statistic never hurts.

Source of the graph I posted yesterday: gist.github.com/cavedave/71d08… x.com/johndcook/stat…

A Box-Cox transformation has the form (y^λ - 1)/λ.

Creative data visualization x.com/JohnDCook/stat…

The square root form of the Kalman filter prevents the potential of negative computed variance due to numerical error.

'The most important aspect of a statistical analysis is not what you do with the data, it's what data you use.' -- Andrew Gelman

Visualization, modeling, and surprises johndcook.com/blog/2013/02/0…

Why are there squares everywhere in statistics (e.g., normal density, variance, least squares, etc.)? statmodeling.stat.columbia.edu/2026/05/16/why…

There is only one test allendowney.blogspot.com/2011/05/there-…

Pianograms: Histograms with piano keys coolinfographics.com/blog/2014/12/4…