In my view, a better means of quantifying political leanings is to use a Mahalanobis metric in high-d policy space https://en.m.wikipedia.org/wiki/Mahalanobis_distance …pic.twitter.com/s8eSxvArZC
Show this thread
-
The 'left-right' axis is the projection of vectors (views) in high-d policy-preference space onto 1st principal component of distribution
Show this thread
I read some article that convincingly refuted the use of spatial modeling in politics of individuals, though I forgot the title.
-
-
Interesting. Definitely curious to see that, if you do recall a title, author, or phrase from the abstract.
-
This one seemed to consider it reasonable-- https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2440781/ …
-
Another, though more relevant to the simpler 2-axis factor model-- https://polisci.wustl.edu/files/polisci/imce/z.spatial.21nov.pdf …
-
This one notes assertions by others that n-dim policy space depiction may be unrealistic, albeit then reformulates-- http://journals.sagepub.com/doi/abs/10.1177/0951692892004001001 …
-
It cites some of the initial work in the area. No free full text though. Might try Sci-Hub. Still a bit old, granted.
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.