The Poisson Process Paradox: Look closely at the questions you’re answering

When it comes to probability the default is always lightning — what are the chances? The quick answer is “not good,” which, it turns out, is good — for you. But there’s more to it than that, especially when you start factoring in semantics and the structural setup of your query. This is something you learn very quickly in research. Throw in a comma, use a synonym or bold a word in your survey or discussion guide and you’ll most likely find your results turned on their head. For example, the sentence “I never said she stole my money” can have seven different meanings depending on which word is stressed.

But, I digress, back to our chance of being struck down from the heavens. I was reading The Better Angels of our Nature by cognitive psycologist and Harverd Professor Stephen Pinker and he raises an interesting question with its roots in semantics and probability — brands often find themselves grappling with similar problems, but instead of paying attention to the question at hand they jump to what seems to be an obvious conclusion.

Supposing you live in a town where homes occasionally get hit by lightning (think one home a month), Pinker asks his students: “Your house is hit by lightning today, Monday. What is the most likely day for the next bolt to strike your house?” Seems pretty straight-forward. But — and I try to impart this on my strategic team– when the answer seems obvious then you’re obviously in trouble. We wouldn’t be paid to solve problems if they were as simple as they appear on the surface.

Facing Pinker’s question, most students (Harvard students nonetheless) answer “everyday has the same chance.” Lightning? Seems random. But nothing is random. Again, if your solution to a strategic problem writes off something to randomness, then you’re in trouble. Suppose the probability of your home being struck by lightning is 0.03. How is choosing Wednesday different than choosing Friday as the follow up strike from Monday? It’s all the same, right? No. For lightning to strike again Friday two things must occur. First, your home has to get hit by lightning. Second, and most importantly, your home has to NOT get hit by lightning Tuesday, Wednesday and Thursday. That’s where we often get tripped up when it comes to problem solving. We ignore what isn’t the problem.

“Your house is hit by lightning today, Monday. What is the most likely day for the next bolt to strike your house?” The correct answer is “Tuesday. Tomorrow.” If you home was as likely to get struck everyday, then the chance would be the same tomorrow as it is 50 years from now. And that would be placing too much emphasis on what’s going to happen instead of what’s NOT going to happen.

The key here is the word “next.” As I teach my team, if there is a word in the question– no matter how small– then consider its importance in the outcome and ultimately your solution.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s