2

In Britain it is generally recognised that opinion polling is not what it once was. At the last two important elections (the General Election of May 2015, and the EU Referendum of June 2016) they have got it horribly wrong.

One of the reasons for this that I've heard given is that telephone culture isn't what it was. There was a time that when a landline phone rang people always answered the call (if they were at home). Modern mobiles as well as landlines give people the opportunity to park calls, and often ignore them; thus distorting results.

Another difference it is said is that modern people do not feel the same compulsion to tell the truth to pollsters as did people of 30 years ago.

I have not seen the same scepticism expressed of opinion polls in the US, and there seems to be more confidence that they have got it right. Is there some reason for this? (It is true that the internet polls in Britain were no nearer being correct than the telephone polls).

  • 2
    I suspect you won't get a good answer to this question until after the election. After all, until the vote happens, we won't know whether the polls were right or not. – Bobson Oct 31 '16 at 11:16
  • 3
    I don't think the Brexit polls were that misguided. Yes, they predicted "No" and it turned out "Yes", but the polls showed a very close margin between the two options, and the victory of the "yes" was a narrow one, too. Take into account that a narrow difference in some states may swing it one way or another, with all of its electoral votes changing completely, so it is a well known risk. – SJuan76 Oct 31 '16 at 11:20
  • When a single poll, the WashingtonPost/ABC poll swings 10 points in a week, we have a problem. Part of it is the sampling methodology, calling people on landlines is outdated. Part of the problem is partisan news agencies. Polling groups will try to get it right at election time so they can claim they had the election "right". So if you see huge swings, like in the WaPo story above, it's almost an indication the outfit was trying to gin the polls to create an "invincible" candidate narrative. Link to the WaPo poll results: – K Dog Oct 31 '16 at 12:55
  • Link to the Wapo Poll results: hotair.com/archives/2016/10/29/… – K Dog Oct 31 '16 at 12:58
  • Recommend something closer to "What factors may be affecting the accuracy of opinion polls in America?" – Drunk Cynic Oct 31 '16 at 13:02
5

Brexit polling

Bloomberg tracked poll results on the Brexit vote. The final value before the election (on June 22nd, 2016) was Remain 46.2% Leave 44.3% with 9.6% undecided (doesn't add to 100% due to rounding). That's a 1.9% margin, well within the margin of error. The actual election was 3.78% in favor of leaving. That's a 5.7% swing. That's large but not unheard of.

Every day leading up to that last polling result, from June 12th to June 21st, Leave was ahead. On June 15th, 3.8% ahead. Then the polling switched back. But in the actual referendum, the result was closer to the June 15th polling result. Maybe it would make more sense to regard the June 22nd polling result as the outlier. Most of the data was pointing the other way.

Another issue is the relatively large undecided contingent. Note that both Remain and Leave outperformed their nominal results in the poll. Did undecideds break towards Leave?

Historical presidential polling

Wikipedia

Some examples from that data:

US presidential polling 1992

In 1992, the final presidential poll result was +12% Clinton. The actual result was +6% Clinton. Both Clinton and Perot showed significantly different results in the actual election. So presidential polling in 1992 was no more accurate than Brexit polling in 2016.

Did the October surprise revelations about a Caspar Weinburger prosecution change things? If so, it's hard to see in the polling, as Bush was essentially flat. It was Clinton's polling that fell.

US presidential polling 1988

Think that 1992 was an exceptionally odd election? Possibly, but in 1988, polling was also off by 5%. Bush had a 12% lead in the last poll but only finished 7% ahead in the actual result.

US presidential polling 1980

In 1984, polling was quite consistent with the final result, but in 1980, we had a 7% swing from Carter to Reagan.

US presidential polling 1976

Only a 3% swing, but from a small lead by Ford to an actual win by Carter. The polls were wrong!

US presidential polling 1964

In polling, Johnson had an 18% lead, but in the election, he only won by 13%. Another 5% swing. Especially relevant in this election with the replay of the Daisy ad. Will that hurt or help Trump?

US presidential polling 1952

A slim 2% lead turned into an 11% blowout for Eisenhower. That's a 9% error.

US presidential polling

I'll leave it up to you to decide whether this is accurate or not accurate. But in US presidential polling terms, the Brexit result would not have been uncommon. The uncommon part is that it crossed the line for victory, not the actual difference between the polled result and the actual result.

Predictions

Absent additional revelations, neither candidate will win a double digit victory. Clinton's +2.8 in the Real Clear Politics average suggests that she has a slightly better chance of doing so. But that could change, as the polls are much tighter this week than last.

Note that the 538 average has Clinton doing better: 49.4% to 44.3%. The 538 average weights polls with greater historical accuracy more highly. That may or may not prove to be accurate. It's worked well in recent elections, but there haven't been enough data points to really evaluate it.

There will be much speculation about the impact of the Comey letter to Congress. There will be little actual evidence of impact though, as the polls were already in motion. Is the additional motion because of the letter? Or previous information sinking into the results? Or random chance? No one will actually be able to tell, but many will opine.

State polling

The national popular vote result doesn't actually matter. What's important is the state-by-state results. There is less information there though. And the polling averages can be slow to update.

| improve this answer | |
  • 1
    On one hand, this is a great answer with tons of research. On the other hand, on a fundamental level, someone as addicted to 538 as me must point out that "polling" is a misnomer - you should not aggregate ALL polls together since they have different methodology, and some are bound to be more accurate than others. – user4012 Oct 31 '16 at 16:20
  • At the May 2015 General Election where the polls were wrong by a considerable factor, the bookmakers got it absolutely right and were quoting an outright Conservative victory as odds on. So at the Referendum I took to looking at the bookies' odds rather than the polls, but on that occasion the bookies were completely adrift, and no doubt paid out a lot of money. It is clear from that, that balancing a betting book, is entirely independent of polling speculation, and simply follows the punters' money. As I write the UK bookies are quoting Clinton at 1-3 on, and Trump at 5 - 2 against. – WS2 Oct 31 '16 at 17:09

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .