William M. Briggs

Statistician to the Stars!

Does watching TV cause autism?

I have no idea, but two gentlemen from the Johnson School of Management at Cornell and one from the Economics department at Purdue seem to think so. They have written a paper, which has found interest at Slate, which they boast as an “exclusive.”

Waldman’s (and others) paper, which is a couple of years old, is a prime example of how to get carried away with an idea, so it is worthwhile to review it. It’s best to download the paper so you can follow along (the paper is freely available).

The genesis of the idea was noticing that autism rates at birth in the state of California started to increase in the early 1970s, picking up pace until 2000, when their data stops (see their Figure 1). It is true to say that something caused this increase. But what?

There is no way to know, but we can posit causes and then test them. The best way to do that is by direct measurement: Propose a cause, design an experiment or collect data in which the cause was controlled and the effect happened. That is difficult to do in the case of autism, of course, since you won’t know a child is inflicted for some time after his birth. But, of course, it would not be ethical to let a cause stay in place if you suspected it would lead to autism. It is also not clear when the cause, or causes, whatever they might be, have to manifest themselves. That is, the same cause might be in place for two children, but miss its timing, so to speak, in the first case and get it right in the second. A plausible biological mechanism for the cause that fits in with other known medical science must also be in place. In short, this kind of investigation is not impossible, but it is difficult and must proceed by, if I can use the pun, baby steps.

Another way to assign a cause is by guessing. This is the easiest method by far. It starts with some guys sitting around a table and saying something like, “How about watching TV? That can’t be good. Especially if kids watched old Three Stooges reruns.” Something like that happened here. Waldman said “I asked around and found that medical researchers were not working on this [possible connection], so accepted that I should research it myself.”

To demonstrate that watching TV is a possible cause involves nothing more than showing that watching TV is correlated (a word I use here in it’s non-technical, plain English sense) with autism. If watching TV had something to do with autism, then the two pieces of data would be correlated, it is true. But if TV had nothing to do with autism, the two pieces of data might still be correlated. The kick is, there is no way to know, by just looking at the TV/autism data, whether this correlation was real or spurious. Of course, autism might be correlated with lots of things, none of which were its cause. This fact means we are on thin ice, and the slightest misstep will cause us to fall through.

Since autism rates have increased since the 1970s anything that also increased, even at different rates, during that same period will be correlated with autism. As the Slate article cautions “petroleum use also rose during the period but is unrelated to autism.” I agree that oil and autism are not related, but you must understand that this is not something which could be learned by examining the data. Oil use and autism are correlated. It is only an extra-statistical judgment that tells us the relationship is silly.

In medicine, there is something called dose response, a fancy way of saying that more of the drug leads to stronger effects (or increased side effects). What might this dose-response be with TV and autism? Well, watching more TV is an obvious culprit: the more hours spent in front of the tube, the greater the chance of developing autism—so speculated the researchers.

But how can you tell how much TV all these kids watched? You can’t. There is no way to go back to 1970 and count how many hours each baby watched TV. This is a dilemma, because we would really like to test the dose-response. Perhaps there is a proxy? A proxy is a stand-in variable that is so strongly associated with hours of TV watched that it’s almost as good as the real thing. Can you think of any?

How about precipitation? Sure, rain and snow. After all, when it rains, what else is there to do but watch TV? Actually, lots, and when it snows, there’s even more. But, this is the proxy chosen by the researchers (their Figure 6 will hold some interest for those interested in global warming).

They plotted up maps by county for California, Oregon, and Washington, and colored in counties that had more than median precipitation (from 1990-2001) and then colored those with higher than median autism rates. These colored squares tended to be in the same spot, and is what led them to the conclusion that watching TV causes autism. Case closed.

But can we think of alternate explanations? Take a look at their Figures 3-5 and you’ll see that the high precipitation counties are all in coastal areas, which are the same places that people choose to live. That is, there is, in these three states, a vastly greater population density on the coasts then in the interior and it is in these regions where the autism rates are higher. Populations in these high-density areas are also more heterogeneous, with greater disparities in behavior, income, health care access, and on and on. Wouldn’t it be more likely that one or more of these disparities were the cause or causes of autism rather than the county’s precipitation rate?

That’s my bet, but again this in a extra-data judgment. The authors of the paper do go on and calculate “linear regression models”, which ties all these and some other variables together. These models have the assumption that everything is related by a straight line, which is probably not true or even a good approximation. But even if they were straight-line related, the models cannot fix the problem that any other variable that increased since the 1970s—like oil use—would have also given significant results. These models only quantify the idea of correlation, after all.

What happens, then, is that these great, complicated tables, built with sophisticated software have given the authors the illusion of certainty. A reporter picks up the story, and then “activists” get involved, and, well, you know the rest.

(Here’s a cute article on other scares, most brought about in the same way as the TV/autism research was done.)

11 Comments

  1. Why would petroleum consumption be reasonably excluded a priori?

    I would think that environmental contaminants might be an easily justifiable explanation, and as the cars from the 70s weren’t the cleanest running, and children, as time continued, probably passed an increasing amount of time in motor vehicles in any case, why could the relation to petrol fuels be excluded only because it seemed “reasofnable” to exclude the relation?

    The health of the human body (as is similar for most animals, methinks) has never responded particularly positively to an increased ingestion, directly or indirectly, of petrol products, byproducts and their exhaust products, as far as I know.

    The correlation would seem similar, and as far as secondary factors (es.: precipitation, which could bring back exhaust into the local biosystem) could reintroduce, maybe even worsenening the case (or improving, in this case, as far as being convincing is concerned), the evaluation would seem quite difficult to quantify…

    But that would be an article for some other evangilist.

  2. Jaqueson really?

  3. An Increase in cases of Autism is likely to be due to increasing numbers of tests carried out to diagnose the condition. Cause: increased public awareness.

  4. This reminds me of the New Yorker writer who rode around the Long Island community that had a cancer cluster fluctuation, saw some power line towers, and came to the conclusion that electromagnetism from the high voltage must be the cause. He writes a piece on it. Fast forward a few years, and we have a judge finding a utility company liable for a litigant’s drop in property values.

  5. Briggs

    July 31, 2008 at 3:13 pm

    Amen, Joy

  6. Jaques,

    there is a higher autism rate now then the 70’s. We have a verifiably much cleaner environment in most areas where it is common now than in the 70’s.

    I tend to agree with Joy about awareness and the default position of people who make money off the condition promoting it. Just like ADHD and similar issues.

    This is a tough one though. Should we agree with them and put a limit on media for children for their own good anyway?? Think of the benefits of children not being awash with the trash from MTV (I am old enough that I don’t even know what is out there now) and similar garbage!!

  7. The rise in the number of telephone area codes correlates very closely. So do snow board sales. What about gravitational effects from the other planets in the Solar System?

    Then there is always the price of tea in China, which seems to correlate with almost everything.

    At one time I had a copy of a study that showed a remarkable correlation between the number of auto accidents and underwear sales in LA, month by month, but I can’t find it. The cause and effect relationship is unclear as to which causes the other but correlations don’t lie.

    Severe autism is no joke. It can be a heavy burden on families. Mild autism, on the other hand, seems to be infecting much of the US population these days. Attention deficit disorder is epidemic. TV, especially 150 channel TV with remote control clickers, gets my vote for the primary causal factor.

  8. The problem of spurious regression is well known in econometrics, and arises from regressing variables with their own particular time series behaviour on each other. The regression then picks up any correlation in the time series behaviour. But there are also diagnostics for spurious regression (a classic signature is high R2 but low Durbin Watson statistics) and ways to avoid the problem by testing variables for stationarity and then using co-integrating regressions. A textbook exposition can be found here

    http://www.oup.com/uk/orc/bin/9780199280964/01student/ppts/ch13/

    especially the last section. And a light approach to co-integration here (teh drunk and her dog)

    http://www.uta.edu/faculty/crowder/papers/drunk%20and%20dog.pdf

  9. Mike D:
    Interesting, do you not think that Tv might be a proxy rather than the cause? Were you joking in your last comment?
    Whether TV is good or bad for kids is not the issue. If we took all TV’s away would ALL the children have a better quality of life? How about the latch-keykids who’s parents may have not the time or inclination to fill in the gap? The reality is that for many children TV does fill a whole. Sad but true. Take it away and there’ll be something else in it’s place that well meaning people will say should be banned as it is causing behavioural problems.
    As for the increasing diagnosis, this is a double wammy. Yes, parents and practitioners are more and in some cases hypersensitive to the condition. Hence less severe cases will be included. Secondly there will have no doubt been very severe cases which were not diagnosed previously as the medical professionals were themselves ignorant of the condition not so very long ago. It would be interesting to see if there was a jump in the numbers after the film “Rain Man” in the eighties. I would expect to see similar numbers for dyslexia.
    There is no reason to assume that the numbers will not plateau if they haven’t
    already. I take your point about our attention span but I’m not sure that this is not
    simply a feature of our ever busier lives rather than a disease. “what is this life if full of care we have no time to stand and stare.” Its a real problem but not the cause of
    autism.

  10. The most likely cause is that areas with higher population density have better hospitals, more money for educational counselors to “root out” cases of autism, and more savvy public servants who know that borderline kids who are diagnosed with autism have lots more public services available to them.

    That’s my “guess.” When do I get published?

  11. The rise in autism diagnoses is more likely to be connected to the expansion of the definition of autism-spectrum disorder and the general growth of the population than to anything else. Persons that circa 1950 would have likely been labeled as “paranoid schizophrenics” for lack of a better term are now being diagnosed as autistic. Also, disorders like Asperger’s syndrome now fall under the autism umbrella.

    Efforts to link autism to the use of ethyl mercury (known also as thimerosal or thiomersal) as a preservative in vaccines have fallen flat; several studies have shown that a) autism rates have continued to rise without a hitch worldwide even though vaccines containing ethyl mercury were being pulled from use as early as 1992 in Denmark, and b) the whole reason for stopping the use of ethyl mercury in vaccines, the belief that it behaved in similarly nasty fashion as its close chemical kin methyl mercury, has been disproved by several studies over the past decade that show that, whereas methyl mercury stays in the body for several months, ethyl mercury is readily excreted from the body within a week — it simply doesn’t hang around long enough to cause any damage, even in the miniscule amounts found in vaccines. That’s why the World Health Organization recommends bringing back ethyl-mercury vaccines for use in developing nations without universal access to refrigeration.

Leave a Reply

Your email address will not be published.

*

© 2015 William M. Briggs

Theme by Anders NorenUp ↑