The 68–95–99 Rule — Normal Distribution Explained in Plain English

It’s a foundational concept in statistics, and the key to understanding a range of natural phenomena

Neil Kakkar
Oct 26, 2020 · 4 min read
Image for post
Image for post

Meet Mason. He’s an average American 40-year-old: 5 foot 10 inches tall and earning $47,000 per year before tax.

How often would you expect to meet someone who earns 10x as much as Mason?

And now, how often would you expect to meet someone who is 10x as tall as Mason?

Your answers to the two questions above are different, because the distribution of data is different. In some cases, 10x above average is common. While in others, it’s not common at all.

So what are normal distributions?

Today, we’re interested in normal distributions. They are represented by a bell curve shape, with a peak in the middle that tapers towards each edge. A lot of things follow this distribution, like your height, weight, and even IQ.

This distribution is exciting because it’s symmetric — which makes it easy to work with. You can reduce lots of complicated mathematics down to a few rules of thumb, because you don’t need to worry about weird edge cases.

For example, the peak always divides the distribution in half. There’s equal mass before and after the peak.

Image for post
Image for post

Another important property is that we don’t need a lot of information to describe a normal distribution.

Indeed, we only need two things:

  1. The mean. Most people just call this “the average.” It’s what you get if you add up the value of all your observations, then divide that number by the number of observations. For example, the average of these three numbers: 1, 2, 3 = (1 + 2 + 3) / 3 = 2
  2. The standard deviation. This tells you how rare an observation would be. Most observations fall within one standard deviation of the mean. Fewer observations are two standard deviations from the mean. And even fewer are three standard deviations away (or further).

Together, the mean and the standard deviation make up everything you need to know about a distribution.

Image for post
Image for post

The 68–95–99 rule

The 68–95–99 rule is based on the mean and standard deviation. It says:

  • 68% of the population is within 1 standard deviation of the mean.
  • 95% of the population is within 2 standard deviation of the mean.
  • 99.7% of the population is within 3 standard deviation of the mean.
Image for post
Image for post

How to calculate normal distributions

To continue our example, the average American male height is 5 feet 10 inches, with a standard deviation of 4 inches. This means:

Image for post
Image for post

Now for the fun part: Let’s apply what we’ve just learned.

What’s the chance of seeing someone with a height between between 5 feet 10 inches and 6 feet 2 inches? (That is, between 70 and 74 inches.)

Image for post
Image for post

It’s 34%! We leverage both the properties: the distribution is symmetric, which means chances for (66–70) inches and (70–74) inches are both 68/2 = 34%.

Let’s try a tougher one. What’s the chance of seeing someone with a height between 62 and 66 inches?

Image for post
Image for post

It’s (95–68)/2 = 13.5%. Both outer edges have the same %.

And now your final (and hardest test): What’s the chance of seeing someone with a height greater than 82 inches?

Image for post
Image for post

Here, we use also the final property: everything must sum to 100%. So the outer edges (that is, heights below 58 and heights above 82) together make (100% — 99.7%) = 0.3%.

Remember, you can apply this on any normal distribution. Try doing the same for female heights: the mean is 65 inches, and standard deviation is 3.5 inches.

So, the chance of seeing someone with a height between 65 and 68.5 inches would be: ___.

34%! It’s exactly the same as our first example. It’s +1 standard deviation.

Conclusion

Knowing this rule makes it very easy to calibrate your senses. Since all we need to describe any normal distribution is the mean and standard deviation, this rule holds for every normal distribution in the world!

The challenging part, indeed, is figuring out whether the distribution is normal or not.

Want to learn more about calibrating your senses and thinking critically? Check out Bayes Theorem: A Framework for Critical Thinking.

Young Coder

Hack. Code. Think. Stories about science, tech, and programming.

Neil Kakkar

Written by

I write about Code and Life philosophies. Sometimes both. | https://neilkakkar.com | Engineer @Bloomberg | Write (Code). Create. Recurse.

Young Coder

Hack. Code. Think. Stories about science, tech, and programming.

Neil Kakkar

Written by

I write about Code and Life philosophies. Sometimes both. | https://neilkakkar.com | Engineer @Bloomberg | Write (Code). Create. Recurse.

Young Coder

Hack. Code. Think. Stories about science, tech, and programming.

Medium is an open platform where 170 million readers come to find insightful and dynamic thinking. Here, expert and undiscovered voices alike dive into the heart of any topic and bring new ideas to the surface. Learn more

Follow the writers, publications, and topics that matter to you, and you’ll see them on your homepage and in your inbox. Explore

If you have a story to tell, knowledge to share, or a perspective to offer — welcome home. It’s easy and free to post your thinking on any topic. Write on Medium

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store