“In general, the most politically intolerant Americans, according to the analysis, tend to be whiter, more highly educated, older, more urban.”https://www.theatlantic.com/politics/archive/2019/03/us-counties-vary-their-degree-partisan-prejudice/583072/ …
-
1) Please take a careful look at methodology: https://blog.predictwise.com/2019/03/the-atlantics-the-geography-of-partisan-prejudice-method-addendum/ …. What you are interested in: the state lines DO have something to do with the data we have to rely on (party counts). FWIW: The methodology is validated (my published paper: https://www.tandfonline.com/doi/abs/10.1080/1369183X.2018.1431109 …)
That paper deals with a different model; that's not validation against ground truth.
-
-
Point: we have validated these models well in general. Here, we have honed in on items that maximize pcpt correctly predicted, but I welcome any advances to the model (possible when we release raw data)
-
Larger point: model miss-specification error would not lead to the phenomena discussed in thread, that is more driven by decision rules we have outlined transparently.
- 1 more reply
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.