In my last post I opinionated about how it's near impossible, in social science research (or media effects, in this case), to account for every possible confounding variable. Now Kevin Drum reviews a new book by Jim Manzi, Uncontrolled, about the same problem, and names it: Causal density. Drum:
If you're studying the orbit of a planet, you can pretty much assume there's only one important cause of the planet's movement: gravity. Causal density is low. In medicine, there are more things to worry about, but a lot of problems are still tractable. Causal density is moderate. But in human affairs, there are lots of causes of everything, there are causes of the causes, and the causes often interact in complex ways. Causal density is very high, which means it's very hard to make sure you've accounted for everything. No matter how sophisticated your statistical tools are, it's always possible that something you haven't thought of is lurking in the background and throwing off your results.
The book is apparently mostly about business and policy, but it looks highly relevant for for social scientists as well. I'm adding it to my stack of books I hope to read sometime soon.
Post Revisions:
This post has not been revised since publication.
Blogging is a dream for me! One of the reasons I got into journalism in the first place was for that friggin' soapbox, or at least a shot at it. With this, anyone can have it!
I have been doing this for about 7 years under a nom de plume. I've posted well over 500 times. Big clue — I used to sit right across from you at the S-T. And my real name is not Scott Bowles, or Mike Dougherty. Enough said until I have my official "last day."
You should start blogging a lot more, and perhaps we can exchange links. Check out my site, please.
Raj! Long time no see!
Heh. Thanks for the link. Indeed I should blog more.
Yeah, I thought of Rajan a bit later. BTW, "Raj" was what he answered to around there, but that's a separate and different name in his culture. He explained to me once that his name is Rajan, so I always called him that. But so many people around the S-T called him "Raj" that he didn't bother to explain any such difference to others. I sat next to him for years, so we eventually had that conversation.
Last I knew of, he was doing OK. Has become sort of a financial adviser to fellow immigrants. Knows the U.S. system well enough to do that.
Unfortunately, his second son is profoundly retarded. We ran into them once in a Jason's Deli restaurant, and his son amused himself the whole time with my wife's bracelets. Janette is a very compassionate and patient person, so we had no other problems. Anyway, Rajan seems to be doing OK, otherwise. But being a caretaker to a kid like that must try one's patience, even when you are his daddy.