Can we anticipate polling error? 📊 July 26, 2020
With 100 days to go, it’s hard to see how Trump stages a comeback
At 100 days before the election, we’d usually be in the middle of convention season—but it’s 2020 and the world is on fire, so this year we’re polling likely boaters instead. Welcome to my weekly newsletter.
I’m G. Elliott Morris, a data journalist and political analyst who mostly covers polls, elections, and political science. As always, I invite you to drop me a line (or just respond to this email). Please hit the ❤️ below the title if you like what you’re reading; it’s our little trick to sway Substack’s curation algorithm. If you want more content, I publish subscriber-only posts 1-2x a week.
Dear reader,
Today marks 100 days until Election Day (depending on how you count). That’s a benchmark that comes with no actual material impacts or meaning, save the fact that it’s a round number and the media likes to use round numbers as pegs for events. But nothing is actually different today.
Yet since other people have already used the round-number excuse, I feel like I’ve been allowed to implicitly. Let’s use the 100-day benchmark to ask an important question: what can change (in the presidential race) between now and Election Day?
A quick note on this blog/newsletter-y thing. I’m doing a bit of website re-coding and re-branding so if the name or appearance of this newsletter changes over the next couple of weeks, don’t be alarmed—that’s intentional. I will explain in due time.
Oh, and sorry for the Monday email instead of the typical Sunday edition; I spent the weekend coding instead of writing.
—Elliott
Can we anticipate polling error?
With 100 days to go, it’s hard to see how Trump stages a comeback
This post is a continuation of sorts of the one I sent out to subscribers last Saturday. In it, we covered the topic of uncertainty in election campaigns, specifically how to think through what information we get from different data—and, crucially, what information we’re missing.
A related topic (and one I’ve been receiving lots of tweets and emails about) is what happens if we see a 1988-type polling error again this year. I have rebutted that such a shift is unlikely now, for multiple reasons. The first is that political polarization has caused election campaigns to be less volatile and easier to predict; fewer swing voters means, well, fewer swings. But the second reason is that when polls miss the outcome of the election they usually miss in the direction of what we’ll expect from other information. In other words, we can often (though not always) anticipate the shift beforehand.
In 1988, the economy was growing steadily and the president for the incumbent party, Ronald Reagan, was also relatively popular with an approval rating around 55%. So when Michael Dukakis’s 17-point polling lead disappeared it shouldn’t have been that surprising.
But this year, the polls and fundamentals agree: Donald Trump is in trouble. The various polling averages have Joe Biden up 8-9 points in the polls and have the president’s approval rating 16 points underwater. The economy is also in tatters (or haven’t you noticed) and the rapid spread and intensification of covid-19 around the country threatens the government’s ability to stage a timely comeback. So, if we think the polls will miss, our best guess is still that Biden will win. That wasn’t the case in 1988, 1992 or 2000, when the polls moved rapidly toward the (more accurate) fundamentals over the course of the election cycle.
Point being: over the next 100 days, a lot can change. But if you want to be empirical and rigorous about forecasting that change, your best bet is still on a healthy (though not assured) Biden victory.
I’m intentionally saying little about the potential uncertainty in this exercise, of which there is a healthy amount. The point is instead to calibrate our expectation of movement over the remaining election cycle, perhaps so that people realize saying “But but but Dukakis was ahead by 17 points in July!” is actually a point for the forecasters, not against them.
Posts for subscribers
July 25: How to think about uncertainty in election models. What can we know (and measure) about the world?
What I'm Reading and Working On
I have been combing through my bookshelf reading the opening few pages of each work of non-fiction I think is relevant to my book project. This helps me get a feel for the right formula for a book introduction (and y’all know how I like formulas), but it’s really just an excuse to procrastinate working on the second chapter…
I have spent a decent chunk of time over the last few weeks revising the presidential election model I put together (with others) for The Economist. We’re trying to do some cool things to adjust for the effects that covid-19 could have on vote choice or turnout, but it’s hard to really test our model robustly because they take a long time to run for each election and there are a ton (think: thousands) of parameters to check. I hope we can have v 2.0 out before the election, but if not, that’s fine as the changes are relatively small in magnitude.
Thanks for reading!
Thanks for reading. I’ll be back in your inbox next Sunday. In the meantime, follow me online or reach out via email if you’d like to engage. I’d really love to hear from you.
If you want more content, I publish subscriber-only posts on Substack 1-3 times each week. Sign up today for $5/month (or $50/year) by clicking on the following button. Even if you don't want the extra posts, the funds go toward supporting the time spent writing this free, weekly letter. Your support makes this all possible!
Photo contest
PS, send me pictures of your pets (or whatever) for the weekly photo contest, which is a thing I just created right now for no particular reason. Maybe I just think cats are cute. The submission email is elliott@gelliottmorris.com.