News for hackers. Stuff that matters.
Re:Heavy drinkers outlive nondrinkers by tkhoven on Tuesday August 31, 2010 @08:44PM (#1651404)
controlling for nearly all imaginable variables - socioeconomic status, level of physical activity, number of close friends, quality of social support and so on

It's been a while since statistics 101, and I'm curious - in practice, how do you control for these variables? Do you try for a large sample size and only compare like with like? Or do you try to estimate the impact of the confounding variables and adjust the numbers accordingly?

There are no comments on this comment yet.