Member-only story

How Statistics Gave the Allied Forces an Edge in World War II

The German Tank Problem with computer simulations

Andre Ye
7 min readMar 17, 2020
German tanks during WWII. Source

It’s World War II and you’re a data scientist (or a statistician, as they were known at the time) for the Allied forces. D-Day is approaching and you need to estimate how many tanks the Germans have. You do know that the Germans have a sequential numbering system (1, 2, …, n), and you know the serial codes for a small sample of captured German tanks. To overshoot the estimation means that resources spent on preparing the Allies for D-Day will not be going to battles in other geographic regions, and to undershoot the estimation could mean a massacre on the shores of Normandy. It’s imperative that you get this number right. How do you go about approaching this problem?

Take a moment and think about it — the statisticians in WWII couldn’t scroll down for an answer!

In this article, I’ll cover:

  • A deeper dive into the German Tank Problem’s historical context.
  • How the historical solution works with intuitive illustrations.
  • Computer simulation experiments and code to further prove its effectiveness.

This is a fascinating example of statistics saving lives. I implore the reader to take their time in understanding…

--

--

Andre Ye
Andre Ye

Responses (3)