What are the Odds?

Humans are bad at decision-making for all kinds of reasons. One of the most important is because we're bad at understanding and making judgments about probabilities.

We've spent the past year+ being forced to make constant decisions about probabilities. For instance, given an infectious disease with a mortality rate of 1.5%, but which is mostly killing older people, but which is also highly contagious, and spread by droplets, but maybe by surfaces... Yeah, do the math. I'll wait.

Let's take a simpler task. The Washington State Department of Health created the graphic below to advocate for mask wearing during the pandemic. And it makes perfect sense. Your risk decreases as people wear masks and separate.

Some took the same idea a step further and added the numbers, identifying the specific risks numerically. The below is from the Rochester Institute of Technology.

OK, now that's specific! First, who understands how these numbers were calculated? Second, now what does this mean? Should I still be worried about 1.5% in that last scenario? Should I ignore masks because the risk isn't zero? Is everything a scam and are all numbers suspect? There are so many reasons we're bad at this, not least because we live in a society that has gone down a rabbit hole of distrust.

But even without distrust and conspiracy theories, we're just bad a math. We don't understand why 70% --> 5% --> 1.5% and we don't understand how someone could have come up with these separate numbers in the first place. And we're really bad at understanding what the numbers really mean. Is 1.5% good or is it still pretty bad?

Think about the blood clots that something like 1 in a million recipients of the J&J vaccine experienced? Is it reasonable to not want that vaccine, knowing the numbers? When we make this decision, do we simultaneously think about what the comparable risks are to our health if we don't take that vaccine?

If you're reading this, I know I'm preaching to the choir. I guess the main point here, for you, is that you probably need to think about your audience for your data content and make sure they have the data literacy they need (and understanding of probabilities and risk) to consume your content.

I'll be having a LinkedIn Live conversation next week with Gini von Courter and Robin Hunt about data literacy and how you can think about this topic when sharing data with your stakeholders. Join us!

==========

Ask me about virtual or in-person data storytelling and visualization training for your team

Learn more about data storytelling and visualization via my other LinkedIn Learning courses.