Strategy. Innovation. Brand.

survivorship bias

Surviving The Survivorship Bias

You too can be popular.

You too can be popular.

Here are three articles from respected sources that describe the common traits of innovative companies:

The 10 Things Innovative Companies Do To Stay On Top (Business Insider)

The World’s 10 Most Innovative Companies And How They Do It (Forbes)

Five Ways To Make Your Company More Innovative (Harvard Business School)

The purpose of these articles – as Forbes puts it – is to answer a simple question: “…what makes the difference for successful innovators?” It’s an interesting question and one that I would dearly love to answer clearly.

The implication is that, if your company studies these innovative companies and implements similar practices, well, then … your company will be innovative, too. It’s a nice idea. It’s also completely erroneous.

How do we know the reasoning is erroneous? Because it suffers from the survivorship fallacy. (For a primer on survivorship, click here and here). The companies in these articles are picked because they are viewed as the most innovative or most successful or most progressive or most something. They “survive” the selection process. We study them and abstract out their common practices. We assume that these common practices cause them to be more innovative or successful or whatever.

The fallacy comes from an unbalanced sample. We only study the companies that survive the selection process. There may well be dozens of other companies that use similar practices but don’t get similar results. They do the same things as the innovative companies but they don’t become innovators. Since we only study survivors, we have no basis for comparison. We can’t demonstrate cause and effect. We can’t say how much the common practices actually contribute to innovation. It may be nothing. We just don’t know.

Some years ago, I found a book called How To Be Popular at a used-book store. Written for teenagers, it tells you what the popular kids do. If you do the same things, you too can be popular. It’s cute and fluffy and meaningless. In fact, to someone beyond adolescence, it’s obvious that it’s meaningless. Doing what the popular kids do doesn’t necessarily make your popular. We all know that.

I bought the book as a keepsake and a reminder that the survivorship fallacy can pop up at any moment. It’s obvious when it appears in a fluffy book written for teens. It’s less obvious when it appears in a prestigious business journal. But it’s still a fallacy.


Now You See It, But You Don’t

What don't you see?

What don’t you see?

The problem with seeing is that you only see what you see. We may see something and try to make reasonable deductions from it. We assume that what we see is all there is. All too often, the assumption is completely erroneous. We wind up making decisions based on partial evidence. Our conclusions are wrong and, very often, consistently biased. We make the same mistake in the same way consistently over time.

As Daniel Kahneman has taught us: what you see isn’t all there is. We’ve seen one of his examples in the story of Steve. Kahneman present this description:

Steve is very shy and withdrawn, invariably helpful but with little interest in people or in the world of reality. A meek and tidy soul, he has a need for order and structure, and a passion for detail.

Kahneman then asks if it’s more likely that Steve is a farmer or a librarian?

If you read only what’s presented to you, you’ll most likely guess wrong. Kahneman wrote the description to fit our stereotype of a male librarian. But male farmers outnumber male librarians by a ratio of about 20:1. Statistically, it’s much more likely that Steve is a farmer. If you knew the base rate, you would guess Steve is a farmer.

We saw a similar example with World War II bombers. Allied bombers returned to base bearing any number of bullet holes. To determine where to place protective armor, analysts mapped out the bullet holes. The key question: which sections of the bomber were most likely to be struck? Those are probably good places to put the armor.

But the analysts only saw planes that survived. They didn’t see the planes that didn’t make it home. If they made their decision based only on the planes they saw, they would place the armor in spots where non-lethal hits occurred. Fortunately, they realized that certain spots were under-represented in their bullet hole inventory – spots around the engines. Bombers that were hit in the engines often didn’t make it home and, thus, weren’t available to see. By understanding what they didn’t see, analysts made the right choices.

I like both of these examples but they’re somewhat abstract and removed from our day-to-day experience. So, how about a quick test of our abilities? In the illustration above, which way is the bus going?

Study the image for a while. I’ll post the answer soon.

Survivorship Bias

Protect the engines.

Protect the engines.

Are humans fundamentally biased in our thinking? Sure, we are. In fact, I’ve written about the 17 biases that consistently crop up in our thinking. (See here, here, here, and here). We’re biased because we follow rules of thumb (known as heuristics) that are right most of the time. But when they’re wrong, they’re wrong in consistent ways. It helps to be aware of our biases so we can correct for them.

I thought my list of 17 provided a complete accounting of our biases. But I was wrong. In fact, I was biased. I wanted a complete list so I jumped to the conclusion that my list was complete. I made a subtle mistake and assumed that I didn’t need to search any further. But, in fact, I should have continued my search.

The latest example I’ve discovered is called the survivorship bias. Though it’s new to me, it’s old hat to mathematicians. In fact, the example I’ll use is drawn from a nifty new book, How Not to Be Wrong: The Power of Mathematical Thinking by Jordan Ellenberg.

Ellenberg describes the problem of protecting military aircraft during World War II. If you add too much armor to a plane, it becomes a heavy, slow target. If you don’t add enough armor, even a minor scrape can destroy it. So what’s the right balance?

American military officers gathered data from aircraft as they returned from their missions. They wanted to know where the bullet holes were. They reasoned that they should place more armor in those areas where bullets were most likely to strike.

The officers measured bullet holes per square foot. Here’s what they found:

Engine                     1.11 bullet holes per square foot

Fuel System              1.55

Fuselage                   1.73

Rest of plane             1.8

Based on these data, it seems obvious that the fuselage is the weak point that needs to be reinforced. Fortunately, they took the data to the Statistical Research Group, a stellar collection of mathematicians organized in Manhattan specifically to study problems like these.

The SRG’s recommendation was simple: put more armor on the engines. Their recommendation was counter-intuitive to say the least. But here’s the general thrust of how they got there:

  • In the confusion of air combat, bullets should strike almost randomly. Bullet holes should be more-or-less evenly distributed. The data show that the bullet holes are not evenly distributed. This is suspicious.
  • The data were collected from aircraft that returned from their missions – the survivors. What if we included the non-survivors as well?
  • There are fewer bullet holes on engines than one would expect. There are two possible explanations: 1) Bullets don’t strike engines for some unexplained reason, or; 2) Bullets that strike engines tend to destroy the airplane – they don’t return and are not included in the sample.

Clearly, the second explanation is more plausible. Conclusion: the engine is the weak point and needs more protection. The Army followed this recommendation and probably saved thousands of airmen’s lives.

It’s a colorful example but may seem distant form our everyday experiences. So, here’s another example from Ellenberg’s book. Let’s say we want to study the ten-year performance of a class of mutual funds. So, we select data from all the mutual funds in the category from 2004 as the starting point. Then we collect similar data from 2014 as the end point. We calculate the percentage growth and reach some conclusions. Perhaps we conclude that this is a good investment category.

What’s the error in our logic? We’ve left out the non-survivors – funds that existed in 2004 but shut down before 2014. If we include them, overall performance scores may decline significantly. Perhaps it’s not such a good investment after all.

What’s the lesson here? Don’t jump to conclusions. If you want to survive, remember to include the non-survivors.

My Social Media

YouTube Twitter Facebook LinkedIn

Newsletter Signup