April 30, 2017

How we Correctly Predicted the Election

Ryan Faulk and I, who own this site, made a number of predictions about the 2016 presidential election:

  1. Trump would win
  2. Trump would out-perform polls, especially in the Rust Belt
  3. Trump would drive new voters to the polls and this would bias pollsters against Trump
  4. The existence of this “monster vote” would be predictable based on primary turnout.
  5. Pollsters were using samples which were biased against Trump in terms of party ID by oversampling democrats and undersampling republicans/independents

Let’s look at how these general points fared and then at the more specific electoral predictions we made. Obviously, Trump won, so we got that right.

Trump over-preformed polls generally (1), but he especially did so in the rust belt:

underprediction-in-america-and-rustbelt

So, we were right about that too. We also said that the polls would underpredict Trump, in part, because they were not picking up on new voters who would vote Trump. We said that the existence of this “monster vote” would be predictable based on the changes in primary turnout for the republican and democrat party.

This would predict that Trump would outperform polls to an especially large degree in the rustbelt:

Primary Turnout in Rustbelt vs America.png

(Primary advantage is defined as the percent change in republican primary turnout relative to 2008 minus the percent change in democrat turnout relative to 2008 (2)).

Of course, Michigan is not in line with this theory. Michigan’s data is misleading. There was a huge increase in democratic primary turnout there relative to 2008 However:

  1. Obama was not on the ballot in the 2008 Michigan primary and this massively depressed 2008 primary turnout
  2. Sanders won Michigan, out performing polls by a huge margin. These were not Clinton supporters.

Given this, our hypothesis is largely confirmed by these numbers so long as you interpret them with a little common sense.

More generally, the bigger the turnout change advantage for the republicans was in a state the less accurate the polls were in that state:

Primary Turnout vs Trump Undeprediction.PNG

The republican turnout advantage also correlated with Trump’s overall margin of victory (r=0.37). So, we were right about the importance of primary turnout aswell.

As we expected, there was indeed an increase in new voters this year relative to past elections. New voters basically always vote democrat because they are typically very young people. Given this, the relevant question when looking at new voters is not whether or not they voted democrat but, rather, by what margin. In 2008, 69% of new voters voted for Obama. This year, only 56% of new voters voted for Clinton. That is a huge drop-off and suggests that Trump did indeed bring in new voters. (I could not find data on 2012).

Thus, the monster vote was real and was predictable based on primary turnout, just as we said it would be.

We also said that pollsters were giving overly pro-Clinton results in national polls because they did not properly weight by party ID. We were right. The Real Clear Politics average for national polls had Clinton winning by 3.3 points on the night of the election. She actually won by 0.2 points. Thus, they were off by 3.1 points.

Five Thirty Eight was even less accurate. They predicted that Clinton would win the popular vote by 3.6 points and so were off by 3.4 points.

I applied the same weighting formula we advocated months ago to  the Bloomberg, IBD, Economist/YouGov, ABC/Washington Post, Monmouth, Ipsos/Reuters, and CBS polls in the final Real Clear Politics average for the election. (The other polls lacked the necessary data.) This changed their prediction from Clinton winning by 3.3 points to Trump winning by 1.8 points. Thus, a prediction based on unskewed numbers would have been off by 2 points, which is about one-third more accurate than the unadjusted pollsters were.

Of course, these polls would have still been wrong by more than we would like them to be. We never said that unskewing would make polls perfect, just more accurate. And we were right about that too.

So, in terms of the general picture, we got this election right. That being said, we did not get every detail correct. This is what I predicted would happen in an article uploaded the day before the election:

0AgWn

I got three states wrong: New Hampshire, Michigan, and Wisconsin.

New Hampshire, I got wrong, but barely. I never said that it would be a landslide, and Clinton won by 0.2%. So I don’t feel too bad about that.

Based on what I have said thus far about our general theory of this election, it may be surprising that I was wrong about Michigan and Wisconsin. I had considered what our theory said about both of them. However, the polls there were really bad for Trump, and I assumed that the “experts” couldn’t be that wrong and so trusted them over my own data and hypothesis. This was clearly a mistake and, moreover, the only major mistake I feel I made when analyzing this election.

 

  1. Polling averages for each state were taken from FiveThirtyEight
  2. Data on primary change was taken from our main article on the subject which can be found here.

 

Facebook Comments
  • NickMane

    Congratulations! Hopefully this will convince some people to no dismiss your other articles.
    By the way, do you think he would have won against Sanders?

    • Ryan Faulk

      No he would have lost because Sanders would win a big chunk of the monster vote and also be less unpopular than Hillary.

      He would have suffered for being an atheist and explicit “socialist”, but he would have carried PA, MI and WI, and that would have been game over.

      • NickMane

        Yeah, that was my instinctual impression.

      • Sean Fielding

        I have to agree that, as a hypothetical, Sanders would have won. Trump’s whole campaign basically represents a vindication for the Sailer Strategy, and he may well have been the only person in America who could’ve imposed it on the GOP and won the nomination, so it’s useless to argue someone else could’ve done better with it than him. And even as the personification of the Sailer Strategy, Trump lost the popular vote and didn’t do all that well with several subcategories of Whites. Since Sanders’ campaign was at least as implicitly White as Trump’s, Sanders would’ve flipped enough White votes to win.

      • Frank Jamger

        I agree with that.

  • Frank Jamger

    Great work!

    I see 5.2 inches of blank space between “when analyzing this election.” and “1. Polling averages for each state…”. You might want to look into that.

    • I use your “14 lists” all the time. Thanks for putting them together. If I may make a request, I need a handy list like this for the negative effects of race mixing if such data is available.

      • Frank Jamger

        You’re welcome. That’s an interesting idea, as it’s true that there are a number of types of negatives that could be categorized and synopsized, such as: erosion of the White genotype and reduction of human biodiversity, outbreeding depression, health problems including STDs, increased familial/societal discord and conflict (including loss of morals), and the personal alienation of not belonging to a group. I think the reason this project hasn’t interested me much is this. The overriding negative effect of race-mixing to me is simply the loss of White traits in children, ultimately yielding White extinction. And the most crucial losses this entails, aside from IQ, are character traits that are hard to define and measure, such as trust and empathy, curiosity and explorative energy, and self-discipline/impulsiveness. (I’m currently working on a project comparing these traits between White/Oriental societies, a big task.) I point out the obvious deficiencies of dark races’ societies compared to ours, though the genetic basis of character differences can only really be inferred from related data (eg IQ studies and simpler biological differences), rather than directly proven in a scholarly way.

        I do understand that the negative short-term consequences of race-mixing are also important to point out. Here are three sources I use, if you don’t have them already, starting with the recent article here by Ryan Faulk.

        Race Mixing
        http://thealternativehypothesi

        Health and Behavior Risks of Adolescents with Mixed-Race Identity
        https://www.ncbi.nlm.nih.gov/p

        Ninety Two Percent: Examining the Birth Trends, Family Structure, Economic Standing, Paternal Relationships, and Emotional Stability of Biracial Children with African American Fathers
        https://papers.ssrn.com/sol3/p

        The site I’m most active on is Twitter, @FrankJ1232.

  • I used your analysis to make good money election night on prediction markets. Thanks for the great data!

  • Riopel

    I was shocked that Hillary won the popular vote, even with her innumerable scandals and obvious mental ailments. If Trump doesn’t follow through on deportations and stem the rising tide of color, he won’t stand a chance in 2020.

    • It’s not clear to me that she really did. Her margin was something like 0.2%. Can we be confident it was a genuine result?