Lies, Damn Lies, and Polls
“There are lies, damned lies and statistics.” — Mark Twain, quoting 19th-century British Prime Minister Benjamin Disraeli
We were the last people to ditch our ancient box TV for a flat screen. Part of the impetus was that I’ve always been fascinated by the small print on the bottom of the screen. Medication and legal disclaimers are still too tiny and go by too fast to read. However, countless medication commercials say in small print, “Actor Portrayal”. The closest they get to honesty is the occasional weight loss commercial: “With diet and regular exercise”, “Results may vary”, “Real people compensated”.
So, watching the news, I look at the small print at the bottom of the screen when polls are being discussed in breathless terms. Seriously, Steve Kornacke of MSNBC is going to have a stroke if he doesn’t slow down. Every conceivable news outlet is braying about the polls.
“Donald Trump is tightening the race!” “Hillary Clinton’s numbers sagging!” “Millennials going Jill Stein!” “Gary Johnson doesn’t know what the hell he’s doing, but Bigfoot’s relatives love the guy!”
I am not suggesting the polls are rigged. But the polls playing on the 24/7 news cycle leave out some important information.
Here’s the deal with the bottom of the screen. A recent number on @MSNBC: “679 of likely voters”.
The fuck? That’s not even the population of MY APARTMENT BUILDING.
Others: “1000 of likely voters” “750 of likely voters” “2000 of likely voters”. Do these sound like representative statistics to you? I live in New York City. These are approximately one city block here.
Before I shoot out my television, Here is a breakdown of the recent CBS polls:
Okay, the methodology is complicated as fuck. But what it amounts to is a small sampling used to represent a national sampling!
Meanwhile, predictions are being shat out all over the place comparing past results to current results. You’re telling me that Obama/Romney 2012 compares in any way to the insane shit show that is our current election? Was one of those candidates batshit crazy?
And consider this, from the September 6 edition of Daily News Bin:
Recent elections have shown that seven percent more registered Democrats tend to vote than registered Republicans, even if they don’t always vote for the party they’re registered to. That means pollsters must decide whether to sample seven percent more registered Democrats in an attempt at getting the most realistic result, or to simply sample both parties equally under the assumption that they’ll end up showing up in equal proportion. But as it turns out, CNN did neither with its poll: it’s suddenly sampling four percent more registered Republicans than Democrats.
Meanwhile, Sam Wang of The Princeton Election Consortium wrote this on September 13:
The Presidential forecast [methods] takes a low-noise snapshot of state polls, then adds possible drift based on recent elections and this year. Because of intense polarization, few voters are movable. The calculation says that Clinton’s win probability is 90%. The Senate forecast does the same [methods], but also factors in Presidential-year or midterm-year bias. It says that Democrats’+Independents’ probability of taking control is 72%, which is in the 20–80% range, meaning that things could really go either way. Other forecasts tend to count uncertainties twice, or to overestimate how movable voters are. Other forecasts are also under commercial pressure to attract eyeballs.
Still, the comment section is still peppered with anxious questions about Clinton’s chances. Honestly, some liberals can be total ninnies. You don’t see the conservatives in hysterics…though actually, here is their version of a meltdown. I take it back. You go.
Yes, that was written over a week ago. I am far from complacent about the polls. I worry that the margins are closing. But considering how small the samples tend to be and how much the 24/7 needs to drive the hysteria of voters (because issues don’t play well), I’m going with Disraeli.