Correlation Does Not Equal Causation

About a week ago, an image came across my desk (via Facebook, if we’re going to be honest here), and since that time I have been trying very, very hard to think of polite ways to phrase my thoughts about it. Tactful ways. Respectful, caring, supportive ways that do not belittle or mock.

I got nothin’.

So here’s some fair warning, ‘Tracters: today you are going to see me be rude, today you are going to see me be all rage-y, and today you are going to read a tirade. There will almost definitely be some pottymouth involved. Those of you who do not wish to participate in my tantrum are welcome to go check out Buzzfeed’s roundup of Red Pandas Who Are Delighted to See You instead.

To those of you who are still here, I present the image which has inspired such vitriol in my icy little heart:

This makes my eye twitch flare up.

This makes my eye twitch flare up.

Some of you may have seen that before, or something similar, and in fact, a good friend of mine posted her own tirade about this topic not terribly long ago. But for those of you who are new to the party, let me condense its message for you:

“Children are receiving more vaccines nowadays. Also, there are more diagnosed cases of autism. Therefore, OMG IF YOU LET YOUR KIDS GET SHOTS THEY WILL GET AUTISM”.

/suppresses twitch

Let me start with a very, very basic math lesson. Actually, no, I’m not even going to call it that, because we’re not going to do any math, though technically this was discussed in that Statistics class I took in college. There’s this principle, see, and I need you to pay very close attention to it; it states that


Those are some big words. Let’s simplify.

Correlation means that you have these two things, and you notice that sometimes they happen together. This is how things like the “lucky underpants” phenomenon arise. For example, you might notice that every blessed time you get your hair done, it rains, because the Universe thinks it’s funny when you cry. You could say, then, that your trips to the hairdresser seem to be correlated to flargin’ blargin’ rainstorms. We know your hairdresser does not control the weather; it just happens to be the case that the two occur concurrently often enough to make you think about buzzing it all off and wearing hats forever.

Causation, on the other hand, means that one thing directly causes the next. The child drops her bowl of cereal; the floor gets all milky and cereal-y. The sun rises; the temperature goes up. It’s measurable, it’s repeatable, it’s verifiable, and–here’s the important part–it is not the same as correlation. These words are not synonyms. They do not mean the same thing. They describe similar phenomena–you observe one thing, then you observe another thing, and the two things seem to go hand-in-hand–but one is a real live honest-to-goodness association, and the other is quite possibly a figment of your imagination (I hate to break it to you, but it’s the “being a great date” that is getting you laid, not your “lucky” underpants with the little ducks on ’em).

Now, it is entirely possible that somewhere down the road, I will eat my words and feel very guilty for daring to imply that autism rates and vaccinations were a relationship of correlation rather than causation. I am open to that possibility.

But in the meantime, all you have are numbers in columns that indicate a correlation between the two…and as a result of that correlation (here’s some causation for you), a lot of parents are freaking out and deciding that they would rather risk having their child die of a completely preventable illness than permitting any possibility that their child will be autistic.

‘Cause, y’know, “Better dead than autistic“.

/suppresses twitch again

In the interest of science, I did a bit of digging of my own. You know what I found?

In 1983 (the same year as in the graphic above) kids got 10 vaccines, the rate of autism was 1/10K, and “Benjamin” was the 32nd most popular name for boys.

In 2008 kids got 36 vaccines, the rate of autism was 1/150, and Benjamin was the 23rd most popular name.

In 2013 they got 46 vaccines, the autism rate was 1/88, and while it’s too early to call the name data yet, as of 2012 Benjamin had jumped to #11.




/smooths down skirt, pats hair back into place

See, that right there is what a hysteria born of a correlation looks like. It’s also why I don’t trust pretty much any statistic anyone ever throws onto a screen nowadays, but that’s beside the point.

The point is that if you’re going to make choices which could directly impact the health of your children and of the children around you (thank you in advance for not letting your measles-bearin’ toddler anywhere near my brand new infant great-nephew, and I’ll ask your forgiveness in advance if I find out that your little plague-bearer–who is THANK GOD NOT AUTISTIC HEAVEN FORBID–has breathed on said great-nephew’s wee tiny no-real-immune-system-yet self and I go upside your head with a kitchen chair or baseball bat or maybe a car), then the least you can damned well do is base your decisions on causation rather than correlation. Y’know, use your damned brain. It’s not just a placeholder in your damned skull. Dammit.


I also have some exceedingly strong opinions about the “better dead than autistic” issue, but I think the nice folks over at Left Brain Right Brain have already handled that for me, and far more succinctly (and with fewer naughty words) than I could manage. So we’ll leave that to them, and I’m going to go take some deep breaths and see if I can’t get this twitching under control.

Before I go, though, let me tie this all up with a neat bow and your official takeaway:


Though really, it’s just correlation at this point. We’ll see if we can prove causation later.



Filed under Don't Make Me Come Down There, General Musings and Meanderings

4 responses to “Correlation Does Not Equal Causation

  1. The part that cheeses me off on this issue – high functioning autistic father of an equally high functioning autistic child – is that these assertions are based upon a study by a doctor whose research was so fraudulent and so damaging that the British government stripped him of his medical license. The study was the product of him Making Shit Up. It’s not that we’re getting more kids who are somewhere on the autism spectrum (when I was a kid, definition was extremely narrow), it’s that the spectrum has been widened to be more inclusive of other disorders: asperger syndrome, sensory processing integration disorder (another fav of mine), etc.

  2. Leah

    I am past the point where I can be polite about this issue. People have tried to persuade me to “open my mind to other points of view” and my answer is, no. Just that. No. To do so would indicate that other points of view are valid on this issue and they are emphatically not. The older I get, the more I learn that, “you’re wrong,” is not only OK to say, but necessary at times.

    • Again, I’m completely ok with the possibility that I will someday be proven wrong, and on that day I will issue a heartfelt apology and retraction on this point. Until that time, I’m with you–some points of view are not scientifically sound, and I simply cannot be persuaded to agree with them. Period. /twitch

Join the Conversation!

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

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ 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 )


Connecting to %s