We could probably substitutre the word 'education' for 'nutrition' in this headline and still have the same article. I read (and you probably do too) a lot of articles relating this or that think to educational outcomes. The more data we get, the more we are seeing these (along with the scatter plots educational economists love so much). But "Big data sets just confer spurious precision status to noise," wrote John Ioannidis in his 2013 analysis. Sure, this article is about foods and nutrition. But it also 'cites' data to show potato chips are linked to higher scores on SAT math vs. verbal. As if. But how many educational studies are reporting noise as if it were fact? A preacher who advised parishioners to avoid trimming the fat from their meat, lest they lose their religion, might be ridiculed, yet nutrition epidemiologists often make recommendations based on similarly flimsy evidence."
Today: 8 Total: 1120 [Direct link] [Share]
View full size
