Statistics in fMRI studies: mere voodoo?
“Do you think the media are partly responsible for sensationalizing the findings of social neuroscience? And how can the media do a better job of reporting on brain scanning data?
Ed Vul: In general, I would advocate a bit more skepticism on the part of reporters, with respect to all scientific findings. I think reporters generally try to write up conclusions in slightly grander terms than the scientists used originally. What they may not realize is that scientists themselves have often oversold the implications of their findings a bit. You put these things together and you can end up with really overblown coverage. (On the other hand, perhaps if this advice were followed, science columns would end up dull and unread, so perhaps I should withdraw the suggestion.).”
This is from an interview of Ed Vul, a graduate student with an inquisitive mind.
Ed Vul
He has an article in press which caused big waves in the small community of social neuroscientists and neuroeconomists. In this paper, he makes a strong critique of the statistical methods used to correlate a behavioral trait with a particular brain region – which is the bread and butter of fMRI studies. For the interested readers, here is the exchange in chronological order:
Ed Vul and al., article in press: Voodoo Correlations in Social Neuroscience
Original Rebuttal by incriminated scientists (including Tania Singer, a neuroeconomist at Zurich), new version of their rebuttal – and they work on an article-length version as well.
Rejoinder by Ed Vul (to the first version of the rebuttal)
Interview of Ed Vul for Scientific American
My bet on the final issue of this debate, for what it is worth? From the quick look I had on the papers, it seems that “regression to the mean” is a central issue in this statistical debate. And ah! if there is one topic where nobody agrees on (among and between statisticians, biologists, and economists), this is this one.* So in my humble opinion, the debate is ripe for taking a turn that is very common in these cases: “It always ends in statistics“. Participants will retort with increasingly sophisticated and intractable analytical refinements, obfuscating the core issue that draw a large audience to the debate in the first place.
neuromanagement.wordpress.com 