It’s a famous example of survivorship bias. The idea is, adding armor to planes make them heavier, so you want to minimize where you put armor. After some flights, you take note of where the bullet holes are in the planes that come back.

Where do you put more armor? Do you put it where there are the most bullet holes? That seems to be where the planes are being shot the most.

The problem is, your sample isn’t representative of your underlying population. These are the planes that came back. If they get shot it the cockpit, they die.

So, where should you put the armor? Well if they can get shot and come back, it’s not all that important, so put it everywhere else.

During WW2, the Allies wanted to armor their planes better so more would survive missions. But armor is expensive and heavy so you'd have to prioritize where to put it.

So they go out and collect data on the returning planes to see where they'd been hit. That picture is basically the data collected: where returning planes had sustained the most damage.

So most of the engineers looked at that and went "Aha, the points with the most damage should be armored, since they get shredded up pretty good."

And one engineer went "Um actually, if they got shot there and came back, armor doesn't matter. We need to armor the spots with no bullet holes, since a plane shot there wasn't able to return."

And so it was, and they called it Survivor Bias.

In this case, it's survivor bias about becoming more conservative as you age

It's an old diagram showing where damage to an airplane could be identified after it returned to base without crashing while still damaged.

In short, the places you don't see damage are parts that the plane can't get hit in if it is expected not to crash before landing again.

Survivorship bias.