For example:

  • When you open a fresh jar of peanut butter do you only work through one side until it is completely empty then start on the other side?

  • Or when you get those shallow tubs of hummus does it have to make it back home undisturbed? Then one of the baggers at the grocery store shoves it sideways into the bag completely ruining the symmetry.

  • udon@lemmy.world
    link
    fedilink
    arrow-up
    1
    ·
    8 months ago

    Well, they don’t say what they mean with “vegetable”, but it’s just put in the same group with gingili oil. I don’t know if you’re in science or otherwise familiar with statistics, but that’s a problematic indication. They don’t justify why they group them, how many of those replied with gingili etc., and they don’t provide a separate analysis. Other major flaws with the study:

    • it’s correlational, but makes a causal inference. That is basic stats, you can’t do that, even if there are no other easy ways to make causal inferences on that topic.
    • the groups vary significantly on many factors, such as total size, smoking status, gender distribution, drinking status etc. They “adjust” for that, but that’s not how “adjusting” works. You can’t just adjust for characteristics of the person and then pretend it’s all controlled for. There is a great paper on this problem, which is unfortunately quite common: doi.org/10.1037//0021-843X.110.1.40
    • smooth_tea@lemmy.world
      link
      fedilink
      arrow-up
      2
      ·
      8 months ago

      I see your point, thanks for the insight! Did you base your reply on the abstract or the full article, because they do specify “vegetable” oil. Also, in their defence, they not only state that they only intended to show a correlation instead of a causal effect, and even add that:

      we only found the relationship between the cooking oil type and cardiovascular health in the elderly over 65 years old in China, and could not explain the reason.