Friday, August 26, 2016

The polls suggest that most of the undecideds will go for Trump

Let's take another look at the Trump v. Hillary polls.

It looked to me like the polls that nudge people toward choosing one candidate or another--as opposed to giving some other answer like undecided, don't know, etc--tend to yield a smaller gap.

I calculated a correlation between the size of the gap and the percentage of people NOT saying Trump or Hillary for the 13 recent surveys listed on either RealClearPolitics or the Huffington Post. I threw them all in there, including the ones I considered to be not-so-great surveys.

The correlation is .38 which means of moderate magnitude. In other words, when techniques are used to get people to take a side, Hillary's lead decreases. When nudged, the uncommitted tend to go for Trump. To illustrate, 23% of Reuters participants fail to give either candidate as their answer, and this poll shows Trump behind by 7 points. With the UPI/CVOTER poll, which managed to get all but 4% to make a choice, Trump came out on top by one point.

So this seems like evidence that the undecideds are leaning Trump, and in the end, most will vote for him. 

Thursday, August 25, 2016

These polls are closer to the truth: Gravis, PPP, Rasmussen, YouGov, UPI/CVOTER, LA Times/USC, and Zogby


The Huffington Post has a useful interactive website where you can compare poll results by several factors. I wanted to look a little closer to see if polls tend to be biased against Trump because some supporters are shy about admitting that they plan to vote for him, and that the methods fail to fully capture the enthusiasm for him.

What you see below is the average Hillary lead by poll characteristics:

Partisan/Registered Voters/Live Phone  11.0

Non-Partisan/Registered Voters/Live Phone  6.2
Non-Partisan/Likely Voters/Live Phone  7.3
Non-Partisan/Registered Voters/Non-Live Methods  5.9
Non-Partisan/Likely Voters/Non-Live Methods  4.8

You can see that partisan polls REALLY favor Hillary. Non-partisan polls that are otherwise the same produce a gap that is 4.8 points smaller (11.0 vs. 6.2 points).

Likely voter polls do not necessarily yield smaller gaps than registered polls, so there is no clear evidence here that registered voter polls are failing to capture the greater support for Trump. On the other hand, it is possible that there are more Hillary supporters who say they are likely to vote but won't actually do it because they can't get excited about her.


Finally, there is clear evidence that the gap shrinks when private methods are used so participants don't have to tell real humans their preferences. The gap shrinks .3 points for registered voter polls and 2.5 points for likely voter polls.

So, the most reliable polls use non-live methods. On the other hand, registered voters polls are not necessarily inferior at this point in the race. Still, it makes sense to give preference to likely voter polls since many registered voters will not actually vote. Based on this, the surveys to place the most trust in (at least the ones that come out frequently) are: Gravis, PPP, Rasmussen, YouGov, UPI/CVOTER, LA Times/USC, and Zogby.  Reuters should also be on the list, but my confidence in them has been shaken. The results are sometimes really weird, and of course, we've seen reporting that suggests they monkey with the data. The good polls indicate Trump is down 4 or 5 points.

Wednesday, August 10, 2016

The best polls indicate a small gap between Trump and Hillary

All the forces that hate Trump--the Dems, the Media, and the NeverTrumpers--are all chanting the phrase that Trump is toast, but the polls have seemed a little off to me for a long time. Audacious has addressed this kind of thing before. The Clinton lead seems to be larger in registered voter polls than likely voter polls, and the gap seems to be smaller with online polls. The first suggests more enthusiasm among registered voters for Trump, and the second suggests that some people might hide their preference for Trump from telephone interviewers.

I created a list of polling companies that were not off by more than an average of 1.5 points in the 2012 election that have also conducted polls in the last two weeks. I predict that the nationwide candidate gap will be largest for telephone surveys of registered voters, and smallest for online surveys of likely voters.

Three polls are live interviews of registered voters--IBD, CNN, and Marist. The mean is a lead of 10.3 points for Hillary.

One poll is an online poll of registered voters--YouGov. It gives Clinton a 7 point lead.

Reuters/Ipsos is the only online poll of likely voters that made my list.  Now Audacious and others have rightly criticized this survey, but I'm assuming they've gotten things straightened out over there. They give Hillary a 4 point lead.

Long story short, Hillary definitely seems to be ahead, but the best methodology produces a small gap between the two candidates, not a large one. And keep in mind that most media polls are of registered voters interviewed by telephone, so the gap is repeatedly exaggerated in the news.

UPDATE:  I checked Reuters latest poll, and it looks like their sample is 44% Democrats and 34% Republicans. That sounds biased to Republicans, but these kinds of numbers are used by polling companies that have been accurate in the past. Evidently, a big chunk of the country has screwy political views, and it's an uphill battle for us to win on the national level.  

Are gun owners mentally ill?

  Some anti-gun people think owning a gun is a sign of some kind of mental abnormality. According to General Social Survey data, gun owners ...