The state of the states in the 2020 Democratic nominating contest
Especially in early states, the contest is still wide open—if you're lucky enough to be polling above 1%
When my computer code finally finishes running and I can send some of the graphics to my coveted newsletter subscribers:
The Takeaway: According to my state-of-the-art average of state-level 2020 nomination polling, Elizabeth Warren is tied with Joe Biden in both Iowa and New Hampshire. She shows all signs of catching up with him nationally any week now. This is an under-covered angle in the primary, but it’s not even the best story in the nomination contest so far. What people are missing is that the race is close—really close—and I’ve got the polling data to prove it.
Editor’s note:
Thanks for reading my thoughts on this subject. And thanks for subscribing! Your membership adds up and makes all this newslettering possible (reminder: I do all this work independently). Please consider sharing online or with a friend; the more readers, the merrier. Remember that apart from getting special articles subscribers can also comment below each post and participate in exclusive threads.
As always, send me your tips about what you’d like to read about next. Or what you don’t want to read. Or your feedback otherwise. Also, cat pictures are nice, so please send them to me! I’m elliott@thecrosstab.com, or @gelliottmorris on Twitter.
Thanks all,
—Elliott
Look, I’m not saying I spent my Saturday afternoon devising a hierarchical Bayesian structural time-series model to average polls of early states’ 2020 Democratic nominating contests that corrects for pollster house effects and gives us a better reading on the race than other currently-available methods, but….
Actually that’s exactly how I spent my Saturday morning! Behold:
You can share this graph if you’d like, but I won’t be publishing the data behind it. This is a work-in-progress for an actual work project—but it was so insightful (and I was proud of myself for getting the statistics to work!) that I felt compelled to share it with you.
What can we take away from this? Well, in each state except South Carolina, look how close all the leading candidates are. Most are within the margin of error with each other, and there is a clear path for a candidate such as Elizabeth Warren to score a big win in an early state and change the state of the race. Although Warren’s estimated support in Iowa might currently be inflated by a too-optimistic-to-be-credible poll in which she was winning 28% of voters, the error is likely smaller than it would be if I wasn’t including pollster house effects.
In other words, what I’ve put together is likely a pretty complete analysis of state-level polls, and certainly better than anything anyone else is publishing right now. We take into account house effects, changing trends at different geographic levels and so much more.
I look forward to sharing more on this soon!