I've tried pointing this out for years now. Can't do a regression and declare, oh, "it's race" when two are linked. http://www.politico.com/story/2017/06/13/trump-white-voters-immigration-muslims-239446 …pic.twitter.com/upSeTeJui3
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Probability models were uninterpretable by most, and no site did a good job. Regression based race/econ "explainers" terribly misleading.
And the aura of science badly done or presented blinded Dems both to the reality, and why their messaging was so weak. So here we are.
What do you mean by "error pattern left unexplained"? This is the literal definition of error in a model: it is unexplained
No, there are multiple sources of error in a model, and in the kind of probability models we had, correlated error was mostly ignored.
No, didn't do a good job presenting correlated error pattern meant, ie correlated state polls are off by 2%, odds go up, say, by 40%.
I agree with this, but do you think that Repubs actually outsmarted dems at their own data game because Rs weren't "blinded" by scientism?
Not the problem. This is the problem https://www.unhackthevote.com/
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.