New work by @fsnole1 et al.: "Sexual Orientation and Involvement in Nonviolent and Violent Delinquent Behaviors” http://link.springer.com/article/10.1007/s10508-016-0717-3 …
-
@KirkegaardEmil You sure love your ggplot2 :) @fsnole1
@AmirSariaslan @fsnole1 What's a better way to visualize contingency tables? In this case, the boxes are perhaps unreasonably large.
-
-
@KirkegaardEmil As an epidemiologist, I’d just prefer the prevalence rates with 95% CIs. @fsnole1 -
@AmirSariaslan @fsnole1 I can add CIs to these if you'd like? :) -
@AmirSariaslan @fsnole1 Here's a logistic model with IQ too. By gender. Note that coefs are reversed.pic.twitter.com/Cyt6Zv7NaL
End of conversation
New conversation -
-
-
@KirkegaardEmil And if you insist on the boxes, I’d rather have them proportional to their respective values. @fsnole1 -
@AmirSariaslan@KirkegaardEmil @fsnole1 A bar chart would make more sense to me. No answer not providing any additional info. -
@ManneGerell@AmirSariaslan @fsnole1 In this case, yes. However, this function is made for any contin. tables, not just with 2 options. -
@ManneGerell@AmirSariaslan @fsnole1 For instance, consider.pic.twitter.com/2rfiCAnBf4
-
@KirkegaardEmil@AmirSariaslan @fsnole1 For that table I'd second Amirs suggestion of proportion over color, or more diff in colorscheme
End of conversation
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.