A new study on political polarization in the United States, conducted by the Pew Research Center for People and the Press, uses large sample sizes, impressive graphics — and lousy judgment.
I have full confidence in the evidence Pew presents. It finds that the number of people with consistently liberal or consistently conservative views on policy has increased, for example, and that ideology and party affiliation are more closely correlated than they used to be.
The trouble with the study is that it can't stop slathering on pejorative descriptions that aren't quite right.