Not sure if bad science also comes here…
A Dutch news website quoted the lancet…
http://www.thelancet.com/journals/landia/article/PIIS2213-8587(17)30307-8/fulltext
Without reading the full report and scolling down to the Declaration of interests… Unilever.
I don’t know. They seem to have identified a pretty strong correlation between the presence of linoleic acid and a lowered risk of developing diabetes, unless there is something wrong with their mathematics or they fudged the data in some way I’m not qualified to detect.
But it’s taking the analysis too far to say that linoleic acid actually prevents Type II diabetes. There I agree with you. It’s entirely possible that some other factor associated with the presence of linoleic acid is what actually prevented the diabetes. The data they analysed are incapable of telling us which.
Thanks PaulL,
I guess (being an engineer) I’ve done some bad Engineering myself by jumping the conclusion 
I like this video where professor Noaks introduces Association studies and how to interpret them. https://www.youtube.com/watch?v=G5KCapZ9tUU&list=PL663N7XRQwA5rahpbpmstcKbH7Oysoo7S&index=13
Hmm isn’t the entire deposition a valuable resource? I sure learned a lot from it.
If you want to get more deeply into the statistical underpinnings of how to assess the significance of a correlation, you could do worse than to read David Colquhoun’s article, “The Perils of P-values.”