2/ Recall bias is a massive problem with these studies. People who consume a product are more likely to recall seeing ads for it. Campaigners prefer to just say “people who see ads for x consume more of x”. The word “remember” is important for the ad to be truthful.
They basically took self-reported advertising exposure, converted into a linear scale, then did the same with self-reported HFSS foods, and used linear regression to estimate the increased consumption
-
-
Then they converted the increased consumption to an estimated calorie intake, based on previous literature, and used that as their final estimate. That's a lot of steps where something could've gone wrong
-
Wow, that sounds even shakier than I expected.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.