US county-level data does not support negative effect of fluoride on intel. True in multi-regression too. http://rpubs.com/EmilOWK/fluoride_water_intelligence_US_counties …pic.twitter.com/5jhRLSVFo8
Study with @piffer_davide (or rather his study, which I hijacked...)
-
-
not that i'm a believer in the fluoride fears, but did you try controlling for % rural?
-
Controlled for spatial autocorrelation via spatial lag. Don't have an urbanity variable. Here's a model with farming occupation. No change.pic.twitter.com/aGBJZcKK2G
-
not sure farming etc are good proxies for rural these days. can't say i've checked tho
-
Then find me some county-level data to use? Not so lazy now. :)
-
just emailed you a file with the data
-
you want to divide rural_pop/total_pop
-
(it's a pretty useful variable generally btw)
- 2 more 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.