Beyond the Rhetoric

 
 
 

Correlation Does Not Imply Causation

January 10th, 2009 by

Correlation Does Not Imply Causation

What’s wrong with this statement?

Children raised in homes with more appliances tend to perform better in school. Therefore, appliances improve intelligence.

That sounds like a pretty outrageous claim, but you’d be surprised how many people fall into this logical fallacy on a daily basis. Just because two events or phenomena tend to happen together does not necessarily mean that one causes the other. Correlation does not imply causation. We shouldn’t assume that the way to improve school test scores is to throw more toasters into the kids’ homes. That obviously won’t work.

With the above example, the “true” explanation brings in a third variable. Generally speaking, homes with more appliances are inhabited by people who are more affluent and have more money. In this way, the parents of these children are more likely to have received more education and have greater resources at their disposal for assisting the kids with their schoolwork. It is (partly) because of this overall higher standard of living and greater level of affluence that the children are performing better in school.

Let’s take a look at another example. This time, the claim does not sound completely outlandish, so we are more inclined to agree with its logic.

Teens involved in violent crimes tend to play violent video games. Therefore, playing violent video games causes teenagers to get involved in criminal behavior.

As much as Jack Thompson would love for us to agree with this statement, its logic is faulty. The claim itself may or may not be true, but it is a logical fallacy to assume that violent video games lead to violent behavior. I’ve played a lot of violent video games in my day and you don’t see me going out on a shooting spree.

The same thing can be said about a lot of things that we hear in the media, like how SUVs cause global warming and increased TV watching results in shorter attention spans. We tend to believe those claims, because they sound plausible. That does not make them logical.

It’s easy to fall into the trap of confusing correlation with causation, especially since this oftentimes happens outside of our immediate awareness. We make little conclusions even without knowing it. Many people emulate their heroes, because they implicitly believe that by wearing the same clothes and having the same mannerisms that they will achieve the same kind of success.

Believe it or not, Andy Roddick didn’t become a good tennis player because he wears Lacoste. He became a good tennis player because he has certain predispositions and he trained for years to master his sport. As a result, he gets paid to wear Lacoste.

Filed under Personal Development.    RSS Feed

Related Reading:

Dot Com Pho: Feeding Dot Com Moguls Since 2001

3 Responses to “Correlation Does Not Imply Causation”

  1. Nick says:

    I certainly agree with what you are saying here. Although, I can’t help wonder if it was influenced by this post

  2. I, too, get a little fed up with folks who automatically assume causation in situations that are really just correlations. However, like the connection between violent teens and violent video games, when a strong correlation exists, it doesn’t hurt to look at it a lot more closely. Consider the correlation, perhaps, a symptom.

    Anne Louise Bannon
    YourFamilyViewer.com

  3. [...] likely that you’ve also had more gliadin in your system too. Good science will teach us that correlation does not imply causation, so it’s possible that the mania is causing the increased level of IgG antibodies and not the [...]

Leave a Reply