George Box All Models Are Wrong Unisex T-shirt

George Box is a legend.

Legendary in his own time, in fact, for penning the words printed on our t-shirt: All models are wrong, but some are useful.

Not available in stores.

A perfect gift for statisticians, data scientists, predictive analytics teams, data miners, and any scientist who works with big data.  

Your statistician friends will love their new shirt. The black on black portrait with white line art is a timeless technique, applied by Brazilian artist Denio Viana.

They will be deeply touched when they receive this from you, because, like, how did you know? This quote is such a deep pull from statistics arcana.  

Here’s a fuller, less pithy version of the idea:

“Since all models are wrong the scientist cannot obtain a ‘correct’ one by excessive elaboration. On the contrary, following William of Occam, he should seek an economical description of natural phenomena.”

Can I get a hell ya?

Honorable mentions for greatest context-free Box quotes go to:

• “the scientist must be alert to what is importantly wrong.”
• “overparameterization is often the mark of mediocrity.”
• “If ‘truth’ is to be the ‘whole truth’ the answer must be ‘No’.”

#IYKYK

If you don’t know George Box, this genius was born in a town with the absolute, stone-coldest name ever. On this there can be no debate. Gravesend. That’s in Kent. Kent’s in England.

George E. P. Box developed the response-surface methodology of statistical modeling. He was moneyballing back in 1951. They weren’t using computers back then, so statisticians needed a faster method to identify which independent variables were impacting the dependent variable (or variables). In the biz, response surface methodology is known as a factorial experimental design.

When the modelers were certain, or at least pretty confident, that all the insignificant independent variables has been discarded and only significant variables remained, then they move on to the more precise and complex modeling techniques to tune up their model.

Response surface methodology bested other modeling techniques of the time because it’s easier and faster, not to mention more reliable. Box and his partner on this method, the right honorable K. B. Wilson, conceded that their new method of statistical modeling, “is only an approximation,” but it worked better. This may be where Box’s argument ending quote comes from.

Other pedantic ninnies argued that Box’s wrongness quote was itself wrong. But we’re not going to get into that here.

Despite Box’s tremendous body of work, he’s best known among non-statisticians for this quote. As for his actual work, the world of statistics saw fit (see what I did there?) to name nine different mathematical devices after him: three tests, three transforms, a distribution, a method, and a design.

1. Box–Jenkins method
2. Box–Cox transformation
3. Box–Tidwell transformation
4. Box–Behnken design
5. Box–Cox distribution
6. Box–Muller transform
7. Box–Pierce test
8. Box's M test
9. Ljung–Box test

LIMITED TIME ONLY!

Offered exclusively to QI Curiosities customers.

Our comfy t-shirt is soft and lightweight with the right amount of stretch.

• 100% combed and ring-spun cotton (Heather colors contain polyester)
• Fabric weight: 4.2 oz./yd.² (142 g/m²)
• Pre-shrunk fabric
• Side-seamed construction
• Shoulder-to-shoulder taping
• Blank product sourced from Nicaragua, Mexico, Honduras, or the US

This product is made especially for you as soon as you place an order, which is why it takes us a bit longer to deliver it to you. Making products on demand instead of in bulk helps reduce overproduction, so thank you for making thoughtful purchasing decisions!

Size guide