As I mentioned in the previous post, I’ve been working on increasing the amount of online content in my introductory biostatistics course; this is part my plan to convert the course into a hybrid course, one which is at least 50% online.
Why does this make me uncomfortable?
Tip from the Geek Press.
So I’ve been preparing a new version of my introductory biostatistics course for the past 2 weeks, and I decided to incorporate most of the videos in the Annenberg Learner online course Against All Odds. One of the videos I’m using is Correlation, which has an interesting discussion on twin studies, addressing the perennial “nature vs. nurture” question. So what do I run across in my daily blog reading, but this Nature Genetics paper, Meta-analysis of the heritability of human traits based on fifty years of twin studies. Talk about luck. One the lectures in a week following the one on correlation is an introduction to meta-analysis. Double play!
Tip from James Thompson at Psychological comments, who seems very pleased with the paper.
So it turns out that being a neatnik is sound economic behavior, at least according to Marie Kondo. So I guess my wife should be some kind of gazillionarie by now.
Tip from the Shirk Report. Why didn’t anybody tell me about this guy sooner?
Looks like potatoes are back on the OK to Eat This list, and the usual thumbsuckers are outraged.
Nutritionist Marion Nestle and other progressive reformers called foul, denouncing the change. “Really?” Nestle scoffed. “I have a hard time believing that WIC recipients are suffering from lack of potatoes in their diets.” Several watchdog groups and the national WIC advocacy group opposed the change, too. “It’s disappointing that politics has trumped science,” Margo Wootan, director of nutrition policy at the Center for Science in the Public Interest, told reporters.
It seems that much of what
our betters the Feds have been telling us about foods and nutrition is a bunch of Just-So Stories:
Rather it’s that the David-and-Goliath narrative of science versus Big Ag may be blinding us to another, even bigger problem: the fact that there is often very little solid science backing recommendations about what we eat.
Most of our devout beliefs about nutrition have not been subjected to a robust, experimental, controlled clinical trial, the type of study that shows cause and effect, which may be why Americans are pummeled with contradictory and confounding nutritional advice.
Any day now, I expect to hear that I should add a shot of tequila to my ideal breakfast of steak and (whole) eggs…and potatoes.
Update (14 April): There’s evidence to suggest that we can improve the good carbs-bad carbs ratio by changing the way we prepare starchy foods. I’ve replaced mashed and roasted potatoes with cooked-then-chilled potatoes (mmm, spicy potato salad).
David Warren, like me, is tired of being beaten about the head and shoulders with observational studies masquerading as “settled science.”
According to the latest research, he writes facetiously, coffee may be good for your heart….Actual science would show the mechanism by which a specific constituent in coffee, such as caffeine, operates within the human metabolism to produce specific reactions in a long, very specific chain, leading to a specific result. … The rest is, to be perfectly colloquial, bullshit,
How many times must we tell the hoi polloi, CORRELATION IS NOT CAUSATION?
Tip from American Digest.
Biologist Austin Hughes hits the nail on the head when the writes of The Folly of Scientism in the New Atlantic.
Central to scientism is the grabbing of nearly the entire territory of what were once considered questions that properly belong to philosophy. Scientism takes science to be not only better than philosophy at answering such questions, but the only means of answering them. For most of those who dabble in scientism, this shift is unacknowledged, and may not even be recognized. But for others, it is explicit.
Don’t believe scientific academics practice scientism? Want to make some heads explode? Just suggest that a logic course, taught in the Philosophy Department, be allowed to satisfy the undergraduate requirement for a math course. Grabbing, indeed.
Tip from American Digest.
Two interesting articles in the New York Times describing the Number Needed to Treat (NNT), the Number Needed to Harm (NNH), have prompted some interesting discussion among ASA members (at the members-only discussion board, unfortunately).
The Centre for Evidence-Based Medicine has a nice technical definition, fans of the NNT have posted a nice tutorial, and Steven Simon has a nice explanation of how to interpret NNT and NNH together. On the other hand, Dr Richard Goldstein at Vanderbilt University offers a webpage-sized grain of salt for interpreting NNT.
I, of course, smell a great homework assignment for my biostats students.