« Statistical thinking on my subway commute | Main | Quote of the month »


Feed You can follow this conversation by subscribing to the comment feed for this post.


1- Those surveys find correlation, never causation, and are quite useless. They've also shown how people don't remember at all what they are during the week, so the correlations found are often not real either.
2- You presume, for your proposed survey, that all GMOs are the same, and different from other foods. Far from the truth of course. A bt crop is very different from a roundup-ready crop, and the biggest difference is not the GMO but the amount of pesticides used to grow them. You'd have to label the food with the protein added by the genetic modification.
3- But then again, why not just study what that protein does when consumed? Then you can create a blind, randomized control trial and actually learn something.
4- Followig your train of thought, we'd have to list on food not just the ingredients but also the strain, the manner in which it is cultivated, and a ton of other stuff. I would actually appreciate that, but would probably not be able to eat anything anymore. :)


Cris: Thanks for the comment. 1 - yes I often criticize nutrition "science" on this blog. however, I think those scientists are doing the best they can given the very difficult problem of not being able to randomize your treatment. In a similar way, I think it is in the spirit of science to make incremental progress, rather than negating all such studies without a viable alternative. 2 - of course, I didn't mean that the particular question will be on the GMO survey. 3 - have anyone done such a study? also, it is quite possible that the effect of GMO is small and accumulates over the long term 4 - one parallel is the polygraph which most scientists agree have no effect but a lot of the public believe it does. So some scientists do studies on polygraphs to prove that they don't work. If we don't label our foods, it is very difficult to do a study.


In an ideal world where everyone is an objective thinker, labeling GMO could be good science. However most people are not objective thinkers, least of all about their own health and its correlates. What these labels lead to (and what the proponents of such labels really want) is that suspicion is cast on GMO products specifically, which will in turn influence people's self-reports - especially if the scientific surveys repeat the suspicion by mentioning GMO.

In order to do objective science in this survey manner, if at all possible, the respondents should list the exact products they've had, and only the researchers should know whether they contained GMO or not. So that in fact speaks strongly against having visible labels on the products.


Mrtos: Your concern is one that is shared by a lot of scientists. We want the government to impose good science on the populace. The problem is that we already allow all kinds of products and services with highly questionable scientific value. Starting with diets, "supplements", "super foods", Fitbits, etc. We also allow cigarette smoking even though we have as solid a science as is possible showing that it causes cancer. There, the accepted solution seems to be labeling!

Re the last paragraph. If you are talking about "ideal", the researchers shouldn't know either. Most researchers are paid for by industry also, which creates a type of problem beyond study design.

The comments to this entry are closed.

Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.
Numbers Rule Your World:
Amazon - Barnes&Noble

Amazon - Barnes&Noble


  • only in Big Data

Next Events

Jan: 10 NYPL Data Science Careers Talk, New York, NY

Past Events

Aug: 15 NYPL Analytics Resume Review Workshop, New York, NY

Apr: 2 Data Visualization Seminar, Pasadena, CA

Mar: 30 ASA DataFest, New York, NY

See more here


R Fundamentals, Principal Analytics Prep

Numbersense: Statistical Reasoning in Practice, Principal Analytics Prep

Applied Analytics Frameworks & Methods, Columbia

The Art of Data Visualization, NYU

Signed copies at McNally-Jackson, NYC

Excerpts: Numbersense Ch. 1, 7, 8. NRYW

Junk Charts Blog

Link to junkcharts

Graphics design by Amanda Lee