A Tangent Trip

Ok, today I am not going to write about writing.  (If you’re disappointed, I’ll try to be back to normal tomorrow.)  Today I am going to have a little tangent about something that’s been bothering me more than usual lately.

“Shopping helps you live longer.”  “Smoking takes 10 years off your life.”  “Hot dogs can give you cancer.”

All of these statements are made based on scientific research.  The problem with them is that most people don’t understand the scientific method, or how experiments are done, and so they don’t take them with the necessary tablespoon of salt.  Why, you ask, should you not just believe these things outright?

It is relatively easy to prove a relationship in a study.  Proving causality is much, much harder.

Let’s take the shopping example, since it’s the least straightforward.  They compared people who were living in Taiwan, how old they are, and how much they shopped.  You can prove there is a link between older age and more shopping; fair enough.  But you can’t prove that the reason they lived longer is because they shopped.  There are lots of other variables that are involved in how long a person lives!

How about the smoking one?  Smoking takes 10 years off your life.  Ok, fair enough, but what if the person in question doesn’t smoke but gets hit by a bus?  Or maybe he smokes, but also eats nothing but bacon and mayo for his entire life?  What if our smokers are also generally unhealthy people in other ways?  Can we truly say that the 10 years they lived less is due to the cigarettes alone?  (I don’t condone smoking, by the way, but it’s an easy example.)

Unless you can eliminate all other variables (which is done in a lab but can’t be done in a study of real people) you usually can’t prove causality.

The other thing that is always left out of the media reports but I guarantee is in the study findings are these two words: “on average.” They take all the cases and average them to find their results.  Saying that the human lifespan is 80 is an average; we understand that some people won’t live that long and some live longer.  The same is true with any scientifically based study, but most people don’t realize that.

Ok, thank you for indulging my tangent about proving causality versus proving a relationship; you may now return to your regularly scheduled day.

Advertisements

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

%d bloggers like this: