(This article was originally published at Statistical Modeling, Causal Inference, and Social Science, and syndicated at StatsBlogs.)
So. A year ago I wrote a Slate article and a blog post (with follow-up here), “19 Things We Learned from the 2016 Election.”
Then Julia Azari wrote “Women Also Know Stuff about the 2016 election,” pointing out that I’d missed a lot of work that was relevant to these questions. Azari wrote:
I’m sure that Gelman’s exclusive focus on work written by men was unintentional. But plenty of women are doing research that is relevant to the points he raises — and some of it even offered insights that turned out to be correct, prescient, and very valuable for explaining what happened in November.
And she was right. I teach in the political science department but I’m not so clued-in about the political science literature.
So Azari and I got together and wrote a joint article which just appeared in the journal Statistics and Public Policy. SPP is a journal published by the American Statistical Association. We probably could’ve published this article in a political science journal but the review process at SPP seemed like it would be simpler.
Here’s the issue of the journal, which contains our article, four discussions, and our rejoinder:
- 19 Things We Learned from the 2016 Election, by Andrew Gelman & Julia Azari
- Unraveling 2016: Comments on Gelman and Azari’s 19 Things, by Jennifer Nicoll Victor
- Response to Gelman and Azari (2017), by Corrie V. Hunt
- What We Learn From Unusual Cases: A Review of Azari and Gelman’s “19 Things We Learned From the 2016 Election,” by Hans Noel
- Response to Azari and Gelman, by Seth Masket
- What We Relearned and Learned from the 2016 Elections: Comment on Gelman and Azari, by Robert Y. Shapiro
- Rejoinder: How Special was 2016?, by Julia Azari & Andrew Gelman
The journal’s html formatting of the articles is pretty ugly so I strongly recommend you click on the pdf buttons at the links to get everything in readable format.
I thank our editors at Slate and Statistics, Politics, and Policy, the five discussants for their thoughtful contributions and especially Julia Azari (whom I’ve never met!) for collaborating on this article.
And here are the 19 things:
1. The party didn’t decide.
2. The ground game was overrated.
3. Overconfident pundits get attention.
4. That trick of forecasting elections using voter predictions rather than voter intentions? Doesn’t work.
5. Survey nonresponse bias is a thing.
6. News is siloed.
7. A working-class pundit is something to be.
8. Beware of stories that explain too much.
9. The election outcome was consistent with “the fundamentals.”
10. Polarization is real.
11. Demography is not destiny.
12. Public opinion does not follow elite opinion.
13. There is an authoritarian dimension of politics.
14. Swings are national.
15. The election wasn’t decided by shark attacks.
16. Red state blue state is over.
17. Third parties are still treading water.
18. Goldman Sachs rules the world.
19. The Electoral College was a ticking time bomb.
Our article concludes:
The 2016 elections have given the paradox of voters who do not follow their party leaders on key issues but remain strongly partisan and predictable in their general-election voting. On one hand this seems inherently unstable—for how long can partisan loyalty be sustained by little more than opposition to the other side—but the combination of winner-take-all elections and (until recently) political gridlock also can make it a hard pattern to break.
The post 19 things we learned from the 2016 election appeared first on Statistical Modeling, Causal Inference, and Social Science.
Please comment on the article here: Statistical Modeling, Causal Inference, and Social Science
