Writers Should Know a Little Something About Statistics

When writers try to interpret research for the general public, it’s often a case of “give an inch and they’ll take a mile.” Too many times, the approach is to make the research support the storyline, rather than the other way around. (Which, in most researchers opinion, is how it should be. Research always starts with a question first, not the answer.)

Starting with the storyline we’re more apt to overstretch research results to make them fit our message. This happens all the time when writers imply causality from correlations. Let’s be clear. The vast majority of research only supports correlations, sometimes strong, other times weaker. But, getting over the correlation hurdle to be able to say X causes Y is both challenging from a research design perspective, and costly.

Some research that would hint towards causal understandings are also often unethical, especially when it comes to research with humans. (For example, the question “does eating high amounts of fat cause someone to gain weight?” is actually an extremely difficult research question to answer.)

Back to the correlation versus causation issue in the media.

I recently finished Tony Robbins’ new book, MONEY Master the Game: 7 Steps to Financial Freedom. It included a ton of interesting information and was well worth reading. But that’s a topic for a different day. It did, however, include a textbook example of presenting something as causative when in fact it’s just a correlation. Here’s the passage:

“There’s the statistical evidence to show that more access to technology can make people happier. The World Value Survey has show that from 1981 to 2007, happiness rose in 45 of the 52 countries studied. And what was going on during those years? That’s right. The digital revolution.”  –pg. 570

Yes, I’m sure greater access to technology plays a role in people’s happiness. But, we’ve also seen the overuse of technology play a role in making people depressed, and unhappy. Also, between 1990 and 2010 (during the same time period people we’re becoming happier), the global burden of mental and substance abuse disorders increased 38%! And, if you look at projections, unipolar depressive disorders will be the number one health burden in the world by 2030 (see chart below).

top 10 leading causes of disease

This is not to diminish the tremendous progress catalyzed by technology and the major improvements in human health and wellbeing over the past few decades. Nor am I saying that overuse of technology is the sole driver of increases in mental illness and disorders. But, things are often the result of a variety of factors; when a number of positive factors come together, good things result.

So, let’s not diminish complexity for an easy headline implying that if we want more of this one thing (happiness) all we need is more of something else (technology). And the next time you read a catchy headline implying causality, proceed with caution!


Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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