There is a raging debate right now about just how close the presidential race is. Is it really that close? Is it time for Democrats to panic? On and on and on. As you may have picked up from my tone I think there’s a lot more heat here than light. Or to put it in statistical terms, the discussion has a high margin of ego and acrimony, even though the actual disagreements seem relatively limited.
The debate between Nate Silver and his critics essentially comes down to the meaning of “close”. At heart there’s an argument here over something that seems as emotive as statistical – how much should we emphasize that while Clinton remains the favorite to win, we can’t take for granted or assume she’ll win? This doesn’t strike me as a truly statistical argument. More concretely, people are arguing over whether the current 538 model is more volatile than it should be, whether it’s picking up a lot of polling noise as opposed to signal. This is a statistical and probability question that is frankly beyond me.
My own beef with the discussion about the state of the race is more philosophical, moral and perhaps aesthetic than statistical. Is it time for Democrats to panic? That’s a hard question for me to answer. Going by an average of public polls the Republican candidate has been behind at every point going back to January. By this measure it’s been “time to panic” and more for Republicans all year. I don’t think it’s ever “time to panic”. It’s undignified and unhelpful. It’s not a good way to live or to think. If you have a lead but the lead isn’t as big as you’d like it to be, is that mean it’s time to “panic”? If you’re panicking in that case how are you going to hold up if you’re behind and it looks like you probably can’t win?
Now, I know the “time to panic” wording is to some degree just a term of art, perhaps even a half sarcastic. But it’s not just that. There’s some deeper issue of penchant for self-blame, lack of focus and a lot of other unlovely qualities. They say a brave person dies only once but a coward dies a thousand times. This is something like that. Sometimes you lose and you have to grapple with that and move on. But there’s a million ways to act like a loser even when you’re winning. And that’s just not a good way to live or approach the world.
With that out of the way, here’s my take on what we know about the election.
First, let’s compare the 2012 and 2016 races. Obviously, we have the full race data set for 2012 while more than a month of 2016 is still to happen. Still the comparison is instructive. I’ve filtered each chart to begin in May.
Here’s 2012 …
And 2016 to date …
A few things immediately jump out. First, the 2012 race is much more stable than the 2016 race. This is likely do to having four candidates, two fairly unliked candidates and a race that is at least to some degree upsetting recent voting patterns. Second, Clinton has maintained a lead at all times. The lead ranges from very small (less than a single percentage point) to fairly substantial (high single digits). (It is important to note that statistically speaking, when you are talking about an average of many polls, a lead of perhaps two percentage points is not a virtual tie.) This captures the key factors in the race. It is close by historical standards but not closer than 2012, judged by the leader’s margin. Indeed, over the course of the period we’re looking at the 2016 margin has usually been higher than 2012’s, sometimes substantially higher.
Does this mean Clinton more likely to win than Trump? Yes. Does this mean it’s close? Yes. Can you just assume Clinton will win and not worry about it? No. Should you channel your anxiety into self-doubt, recrimination and drama? Please don’t. Pretty much everything else seems like a matter of semantics.
My own hunch is that that line separating the two candidates is likely more durable than some suspect. But that’s just my own hunch.