Tuesday, September 29, 2009

Why do we overinterpret study findings?

MSNBC recently reported that a new study suggests "U.S. states whose residents have more conservative religious beliefs on average tend to have higher rates of teenagers giving birth". (I learned of this on Rationally Speaking.) The study itself is Open Access, so all the details are freely available. The scatterplot illustrates the strong association the authors found. Now, the authors were reasonably cautious in how they interpreted their findings. The trouble is, the general public may not be.

A common error is to conclude the study shows that religiosity causes higher teen birth rates. But correlation does not imply causation. It could be that higher teen birth rates cause religiosity. Or perhaps a third, unidentified factor causes both.

But isn't the strength of association still impressive? It is. But what if, as I just suggested, there are other variables involved? Such confounding variables (or confounders, as they are commonly known) can wreak havoc on this sort of analysis. Indeed, the authors of the study did adjust for median household income and abortion rate (both at the state level). But it is possible that other confounders are lurking. And unfortunately, we tend to forget entirely about the possibility of confounders when we hear about study findings.

Another error is to conclude that the findings directly apply to individuals. Here I will quote the authors directly:
We would like to emphasize that we are not attempting to use associations between teen birth rate and religiosity, using data aggregated at the state level, to make inferences at the individual level. It would be a statistical and logical error to infer from our results, “Religious teens get pregnant more often.” Such an inference would be an example of the ecological fallacy ... The associations we report could still be obtained if, hypothetically, religiosity in communities had an effect of discouraging contraceptive use in the whole community, including the nonreligious teens there, and only the nonreligious teens became pregnant. Or, to create a different imaginary scenario, the results could be obtained if religious parents discouraged contraceptive use in their children, but only nonreligious offspring of such religious parents got pregnant. We create these scenarios simply to illustrate that our ecological correlations do not permit statements about individuals.
To err is human ...

My goal here has not been to criticize the authors of this study, nor the media. Rather, what I find remarkable is how such a simple statement—"states whose residents have more conservative religious beliefs on average tend to have higher rates of teenagers giving birth"—can be so easily misinterpreted, and in so many different ways! Does anyone know of any research about our tendency to overinterpret scientific findings? Of course, we'd probably overinterpet it.

Labels: , , , ,

Bookmark and Share

Sunday, September 20, 2009

War is bad for your health

U.S. health care spending per capita is the highest in the world. Yet, as The Economist notes, "America lags behind other wealthy countries in the overall performance of its medical system". It might seem ironic then, that the same magazine has stated that the U.S. "offers the best health care in the world." But keep reading:
If you are lucky enough to have proper insurance and be admitted to the Mayo Clinic, the UCLA Medical Centre or Johns Hopkins, you will enjoy outstanding treatment. Unfortunately, as the tens of millions of uninsured and underinsured have discovered, America offers some of the most unreliable, costliest and least equitable health care in the world too.
The U.S. spends around 17% of its GDP on health care. This compares to Canada where we have a publicly-funded system, and spend around 9%.

Now there are lots of complexities here and I don't mean to oversimplify. The Canadian health care system is far from perfect, although I think most Canadians are bemused by the outlandish depictions some American demagogues present. In any case, the fact is health care costs have been spiralling here just like in the U.S. As President Obama struggles to enact health care reform, people wonder, "Where will we get the money?" Canadians are asking the same question.

Meanwhile, somewhere in Asia ...

... we have some nasty little wars going on. According to the Center for Arms Control and Non-Proliferation, the U.S. spends $771 a second on Afghanistan and $3973 a second on Iraq. Oh, that's $2 billion/month and $10.3 billion/month respectively. Canada isn't involved in Iraq, but the total projected costs of the Canadian involvement in Afghanistan are "up to" $18.1 billion. (Those quotes express a certain skepticism on my part.)

And how are things going in Afghanistan?
Overall security conditions throughout much of Afghanistan continued to deteriorate during the quarter. In May and June, the frequency of insurgency attacks nationally was higher than in any month since the fall of the Taliban regime in 2001.
The CBC reports that, to date,
Since 2002, 131 Canadian soldiers have been killed serving in the Afghanistan mission. One diplomat and two aid workers have also been killed.
There is no mention of Afghans. Nor—and this raises another point—is there any mention of soldiers who were wounded. Soldiers who may well require ongoing medical care. And how do you measure the costs of post-traumatic stress disorder?


We are pouring money down the drain on unnecessary, unwinnable wars, all the while wringing our hands about where we'll get the money to pay for decent health care.

Labels: , , , ,

Bookmark and Share

Friday, September 04, 2009

Why philosophical zombies matter

I first wrote about the mysteries of consciousness on this blog back in February 2006. This prompted me to do some reading on the philosophy of mind, and in March 2006 I wrote more about consciousness.

Though I didn't mention it directly in that post, a very compelling argument concerns what are called philosophical zombies. I would put the argument like this. First, ask yourself: Is it conceivable that there could be a thing that appears to be human but in fact has no conscious experience? In other words, a biological machine, identical to a human in every way, except that it has no free will, feels nothing, experiences nothing. To put it bluntly, a zombie.

If your answer is no, then I would ask this: How can you know that some of the "humans" around you are not in fact zombies? Is there a device available that will measure consciousness? Granted we have tools that can measure aspects of the complex electrical and chemical activity in the brain. But complex electrical and chemical activity is not consciousness. Consciousness has to be experienced. And there's the rub. We can be sure of only one person's consciousness: our own. As Descartes famously noted, "I think therefore I am". Continuing to follow this line of reasoning can lead to solipsism, but that's not my point at all. Rather, I believe that the philosophical zombie argument provides one indication that there is more to the world than the material.

In response to this argument, people will sometimes steadfastly maintain that consciousness is nothing more than complex neurological activity. When I point out that there's no reason to believe that such activity has to be accompanied by consciousness, the response has sometimes been to deny consciousness itself! Which brings me back to the cartoon at the start of this post. Someone who denies their own consciousness could only be a zombie!

Labels: , ,

Bookmark and Share