Hal Varian, Chief Economist of Google declares: “The ability to take data – to be able to understand it, to process it, to extract value from it, to visualize it, to communicate it – is going to be a hugely important skill in the next decades.”
Wow. There’s so much being said in that one sentence.
Let’s take his first condition of “to be able to understand it” and dive a bit deeper into what he’s saying here.
For this, I’m going to share a story about military airplanes flying missions during World War II.
As these planes were attacking targets over Germany, many were lost or damaged in the process.
The Department Of The Navy wanted to protect the planes and pilots as much as possible, but were unable to reinforce the entire plane due to weight restrictions.
To identify the most critical areas, they brought in a team of statisticians to help analyze the data.
The team studied the damaged planes and saw the bullet holes were located on the fuselage, wings, and tail section … with very little damage to the engines and cockpit areas.
Seeing this, it only made sense to reinforce those areas with the most damage.
Or did it?
Not according to Abraham Wald, an abstract thinker who concluded they should reinforce the areas WITHOUT bullet holes … because the data wasn’t telling the whole story.
See, their input data was only collected from the planes that survived – which means that if they got shot in the engine or cockpit, the bomber never returned home to be included in the study.
It’s not always easy to know which insights matter most, but by keeping the bullet hole fallacy in mind and asking further questions (such as ‘why are there no holes in the engine bay?’) you’ll dramatically increase your chances of reaching the right conclusions.
