December 2, 2016 11:55 AM
The Polling (and Other Measurements)
The general perception is that the majority of the polling profession blew the 2016 presidential campaign.The Real Clear Politics list of surveys taken over the period 11/2-11/7 showed Hillary Clinton with a lead of 3.3% over Donald Trump in the four-way race and 3.2% in the two-way race.
Pollsters note that Clinton won popular vote…so polls showing Clinton ahead by 1 or 2 points, were most accurate. The Pew Research Center did an article on November 9th that had the following headline, “Why 2016 election polls missed their mark.”
The following are a few excerpts from the Pew article.
“How could the polls have been so wrong about the state of the election?”
“There are several possible explanations for the misstep that many in the polling community will be talking about in the coming week.”
“One likely culprit is what pollsters refer to as the nonresponse bias. This occurs when certain kinds of people systematically do not respond to surveys despite equal opportunity to reach all parts of the electorate.”
“Some have also suggested that many of those who were polled simply were not honest about whom they intended to vote for.”
“A third possibility is the way pollsters identify likely voters…This is a notoriously difficult task, and small differences in assumptions can produce sizeable differences in election predictions.”
On the other hand, Frank Newport who runs Gallup authored an article on November 23 entitled, “National Polling Accurately Nails Popular Vote.”
The following are excerpts from his article.
“This was a complex election since Hillary Clinton won the popular vote and Donald Trump won the Electoral College. In terms of forecasting, being ‘right’ means two different things, depending on whether you were estimating the former or the latter.
“Many people most likely assume that any poll at the national level is forecasting the electoral outcome, which is actually not the case. National horse race polls predict the national horse race – the popular vote. Given that in two of the last five elections the popular vote winner did not win the Electoral College (and the presidency), the distinction between the national horse race polls and efforts to predict the Electoral College become more significant.”
“In terms of predicting the national popular vote outcome, the national polls did remarkably well in 2016. As was the case in 2012, the Democratic candidate’s popular vote margin is growing as vote counting continues in the weeks after Election Day. As of this writing, Clinton is ahead of Trump by 1.5 percentage points…The margin could grow to two points. Clinton will therefore win the popular vote by a larger margin than was the case of Al Gore over George Bush in 2000, Richard Nixon over Hubert Humphrey in 1968 and John F. Kennedy over Richard Nixon in 1960.”
“The average ‘gap’ estimate on the national popular vote as calculated by Real Clear Politics prior to the election was 3.3 points…To come within less than two percentage points on the gap is a remarkable polling achievement and should be applauded.” (Gallup decided not to poll the 2016 presidential campaign.)
Newport added, “To the degree that organizations want to predict the Electoral College, they are going to have to find ways to finance or encourage larger-sample, higher-quality state polls, rather than relying on the haphazard polls that happen to be conducted in various states.”
In the 11/2-11/7 period, CBS News had Clinton up by 2, Bloomberg and Reuters/Ipsos had Clinton up by 3 points. In that same period, Economist/YouGov, ABC/Wash Post Tracking, Fox News, Gravis, NBC/WSJ had Clinton up by 4, and Monmouth had Clinton up by 6.
Only one survey using traditional survey methods, IBD/TIPP, had Trump leading by 2 points.
The bottom line is, if you take the RCP average Clinton lead of 3.3% and Clinton’s current popular vote lead of 2% the difference is 1.3%. The margin of error of the relevant surveys is 3.3%. Thus, as Gallup points out, the result of these surveys is well within the margin of error.
If by chance you are looking for other ways to predict presidential elections here are a couple of options.
Well before the November election Allan J. Lichtman, a professor of history at American University in Washington, DC, predicted Donald Trump’s victory. He has successfully predicted the presidential election victor in every presidential campaign since 1984. He makes his predictions based on 13 true/false statements that he says indicate whether the incumbent party will retain the White House or lose it in a given election. His list of true/false statements includes such things as:
Q.1. Party Mandate: After the midterm elections, the incumbent party holds more seats in the U.S. House of Representatives than after the previous midterm elections.
Q.13. Challenger charisma: The challenging party candidate is not charismatic or a national hero.
For the remainder of the questions see the May 12, 2016 article in The Washington Posts’ The Fix by Peter W. Stevenson.
In the last nine presidential elections the golfer has defeated the non-golfer. The last non-golfer to win was Jimmy Carter. Since World War II, golfers have beaten non-golfers in 16 of 18 presidential races. Harry Truman was the only other exception. [Don Van Natta, Jr., ESPN]
