In 1990, about 8 percent of the US population had no religious preference but by 2010, this percentage had more than doubled to 18 percent. That's a difference of about 25 million people, all of whom have somehow lost their religion. Now MIT Technology Review reports that Allen Downey, a computer scientist at the Olin College of Engineering in Massachusetts, has analyzed the data in detail and says that the dramatic drop in religious affiliation is the result of several factors but about 25 percent of the drop is due to the rise of the Internet. Downey concludes that the increase in Internet use in the last two decades has caused a significant drop in religious affiliation: for moderate use (2 or more hours per week) the odds ratio is 0.82. For heavier use (7 or more hours per week) the odds ratio is 0.58.
What Downey has found is a correlation and any statistician will tell you that correlations do not imply causation. But that does not mean that it is impossible to draw conclusions from correlations, only that they must be properly guarded. "Correlation does provide evidence in favor of causation, especially when we can eliminate alternative explanations or have reason to believe that they are less likely," says Downey. It's straightforward to imagine how spending time on the Internet can lead to religious disaffiliation. "For people living in homogeneous communities, the Internet provides opportunities to find information about people of other religions (and none), and to interact with them personally," says Downey. "Conversely, it is harder (but not impossible) to imagine plausible reasons why disaffiliation might cause increased Internet use."
There is another possibility: that a third unidentified factor causes both increased Internet use and religious disaffiliation. But Downey discounts this possibility. "We have controlled for most of the obvious candidates, including income, education, socioeconomic status, and rural/urban environments. (PDF)" If this third factor exists, it must have specific characteristics. It would have to be something new that was increasing in prevalence during the 1990s and 2000s, just like the Internet. "It is hard to imagine what that factor might be."
(Score: 5, Informative) by MrGuy on Thursday April 10 2014, @04:12PM
So, I applaud TFA (and TFS) for drawing a good line between correlation and causation. And the author is right - sometimes correlation IS because of causation.
That said, starting with a correlation, simply to speculate "I could imagine a mechanism..." doesn't make a terribly convincing argument. Nor does "I think I've controlled for everything else, so this is the only thing that remains and so I guess it must be the cause."
What DOES make a convincing argument is exploring various likely implications of your hypothesized mechanism, and seeing whether those predictions bear out.
The author suggests a mechanism where internet use exposes members of insular communities to wider ideas and other faiths, and makes those individuals more likely to question their faith. Great. You can test that. If it were true, I'd expect to see more of a drop in rural areas (where it's easier to have a sheltered community) than urban areas (where it's harder to avoid exposure to outside ideas). I'd expect to see more of a drop in communities in areas where a push to universal broadband was happening than in areas where there was no such push. I'd expect the Amish to see relatively little decline. I could see doing some really interesting testing around Utah (which has both large and strong religious communities, and challenges setting up connectivity given the terrain of the state).
If the dataset being used is large enough to test these secondary hypotheses, then the study author is doing himself and science a disservice by speculating where he can test.
(Score: 3, Informative) by MrGuy on Thursday April 10 2014, @04:20PM
Apologies - apparently special characters get stripped in post titles. "Correct" thread subject had a ">" sign in there.
Live and learn.
(Score: 3, Funny) by martyb on Thursday April 10 2014, @04:48PM
Yeah. Character entities are your friend. Use ">" when you want to see a ">".
And, to keep this somewhat on-topic, then pray. =)
Wit is intellect, dancing.
(Score: 2) by mattie_p on Thursday April 10 2014, @04:59PM
I've noticed this in story titles as well. I think it is because slashcode needs the escape characters for certain symbols. If you use the html escape code > it should work. See?