I'm a bit lost for words. The study: - case-control (observational) - 240 participants - logistic model with ~25 covariates (!) - one significant result (pre-school screen time) Headlines:pic.twitter.com/Kd4oLmw1yS
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Hard to blame the journos for this one tho, the study itself is pretty questionable. Not sure how you justify using logistic regression to analyze 25 covariates with such a small sample size
The conclusions, for example, argue that exposure to screens is a significant public health issue even though the results were negative for most markers of screen exposure? So weirdpic.twitter.com/6ssCs00o6l
Things that didn't increase risk of language disorders in children:
- more screen time
- screens in holidays, during meals, during the school day, after school etc
- having the tv on more often
- the age that kids were first exposed to screens



That being said, if my translation's correct the scientists basically said "this is an interesting association that should be studied more", which doesn't really come through in the headline!
did they run a test to estimate likelihood of at least one statistically significant finding completely by random chance, given the number of tests run?
What’s the outcome below with an OR of 4!?!?! 
screen during lunch
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.