Tardiness solves statistics theorems

Posted to Statistics  |  Nathan Yau

Yeah, you read that right. Tardiness makes the world go ’round:

One day in 1939, Berkeley doctoral candidate George Dantzig arrived late for a statistics class taught by Jerzy Neyman. He copied down the two problems on the blackboard and turned them in a few days later, apologizing for the delay — he’d found them unusually difficult. Distracted, Neyman told him to leave his homework on the desk.

On a Sunday morning six weeks later, Neyman banged on Dantzig’s door. The problems that Dantzig had assumed were homework were actually unproved statistical theorems that Neyman had been discussing with the class — and Dantzig had proved both of them. Both were eventually published, with Dantzig as coauthor.

Other benefits include more hours of sleep, exercise while power-walking to your destination, and all-around warm, fuzzy feelings knowing that you live by nobody’s schedule. You might also supposedly inspire films like Good Will Hunting.

Who knew?

[via Bobulate]


  • Nice… unwittingly solving unsolved problems sounds like a pretty good outcome.

  • threebears July 22, 2010 at 6:39 am

    Nice. What I don’t get is why Dantzig was only co-author, surely if he solved the unproved statistical theorems …..?

    Tardiness is often caused by extreme (and unrealistic) optimism. That’s my excuse.

    • That’s grad school for you :)

    • The co-author situation happens a lot in grad school, but it does make sense. The prof probably spent a *lot* of time verifying that they were indeed proofs. Having a better-known name on it also gets it a bit more legitimacy, as otherwise you get shoved into the pile of potential-crackpots.

  • Great story. Maybe its worth mentioning that Dantzig is the father of Operations Research. He invented the Simplex Method (Linear Programming).

  • It all goes to show that Statistics and Operations Research do work together!! Another point about Dantzig is that he was devoted to applying mathematics to environmental issues later in life. It is a testament to his genius that he invented a robust, easy method to solve linear programs which is still in wide usage.

  • Maybe that’s why classes at Berkeley run on “berkeley time” — they all start 10 minutes late.


10 Best Data Visualization Projects of 2017

It was a rough year, which brought about a lot of good work. Here are my favorite data visualization projects of the year.

Marrying Age

People get married at various ages, but there are definite trends that vary across demographic groups. What do these trends look like?

Shifting Incomes for American Jobs

For various occupations, the difference between the person who makes the most and the one who makes the least can be significant.

Reviving the Statistical Atlas of the United States with New Data

Due to budget cuts, there is no plan for an updated atlas. So I recreated the original 1870 Atlas using today’s publicly available data.