data for politics #15: Unions fight fascism

Sean McElwee (@SeanMcElwee)

In my last blog, I walked through what predicted support for Trump among white voters. See here for that piece (including data and model specification). 

Here, I quickly analyzed one thing that might predict opposition to Trump: being a union member. I ran a multinomial logistic regression including three outcomes: Clinton, Trump and another candidate. I then calculated the conditional marginal effect of each variable, which were all coded as binaries for simplicity (i.e. 0 or 1) holding all other variables equal. "Current union" indicates an individual is at the time of the survey a union member. As with the models in the last piece, I only examine white voters.

Unions fight fascism.

unionsfightfacism.png

Sean McElwee (@SeanMcElwee) is a co-founder of Data for Progress.