- Joined
- Feb 24, 2013
- Messages
- 40,528
- Reaction score
- 24,157
- Gender
- Undisclosed
- Political Leaning
- Conservative
The “Red” vs. “Blue” Crime Debate and the Limits of Empirical Social Science
Our analysis, however, makes a very simple point: it is very easy to change the conclusion by manipulating the data in very simple ways. Increasingly complicated analyses will not get rid of this fact but instead will open even more opportunities for manipulation. In a very real sense, the sign and magnitude of the correlation between the Trump share of the vote and violence ultimately depend on whatever the researcher wishes to do with the data.It seems to us that it would be far more productive to spend that time and effort debating the merits of actual policies, as opposed to measuring the effect of partisan leanings in the population. Democrats say that lax Republican gun laws drive up murder; Republicans say that Democratic mishandling of policing and prosecution is what really matters.Let’s have those discussions, rather than interminably going back and forth over whose constituents are more violent. The U.S. certainly has more than enough murders to go around.
That's the dumbest pretzel logic study I've ever read. "Adjusting for Urbanization" is the statistical way of saying they diminished the urban violence impact and it makes the Blue-vs-red differences disappear, which is the equivalent of saying that Blue counties aren't more violent when you don't include cities in the evaluation.

Also interesting that they found that there was no violence difference between blue and red counties when you did the same trick as above but with race, age and gender. When you realize what this is saying you'll like the actual conclusion that this study is skirting even less.
Last edited: