Going into the final few days of 2016 US presidential election, we were told by pollsters that Hilary Clinton was certainly going to win.
American statistics and polling analysis site FiveThirtyEight stated that Clinton had 71.4% chance of winning the presidency and, being generous enough, they gave Trump a 30% chance of winning.
Some even said Clinton had a 99% chance of winning. Sam Wang at the Princeton Election Consortium estimated Trump's chances at less than 1%, and even pledged to eat a bug if Trump earned more than 240 electoral votes, which he later did!
Four years on, the memory of Donald Trump's surprise victory in 2016 still haunts forecasters and pollsters and they certainly did not want to eat bugs. This time, over the last few weeks, we were told why the pollsters would not be making the same mistake again.
Averages of high-quality surveys – those done on telephone, not online, and with track records of accuracy – showed Biden leading in the three Midwest states of Wisconsin, Michigan and Pennsylvania that gave Donald Trump the presidency in 2016.
Shibley Telhami, a pollster and professor of political science at the University of Maryland told Al Jazeera, "Any real objective analysis, including an objective comparison to 2016, would lead you to believe that Trump's situation is pretty much hopeless."
Also, looking at the political polling data, it would seem obvious that Democratic presidential candidate Joe Biden is winning the election.
And yet, irrespective of who finally wins the US election, it is clear Trump has made a fool of the pollsters once again. The US President was told to expect 'landslide' in election. During an interview with Andrew Neil on TimesRadio, journalist and biographer Michael Wolff said Donald Trump will suffer a "landslide" defeat to Joe Biden in the 2020 US Presidential election. "Everyone knows it is going to be a landslide, but is it a 45-state landslide?" added Michael.
But, the reality sunk in the minute Florida started reporting its election results. And, at the time this report was filed, Trump already won 22 states amongst the 50 US states.
Apart from Brexit Party leader Nigel Farage and Des Moines Register/Selzer and Co. poll from Iowa, almost everyone, including Republican pollsters predicted a Biden win.
The consensus of major national polls tracked by FiveThirtyEight gave Biden a stunning 8.4 percentage point lead on 1 November. The Economist on November 3 predicted that Biden has 97% winning chance. The New York Times also said that Biden will end with a commanding lead.
"If Biden wins what would the first 100 days of his presidency look like?" an article published by The Guardian discussed what would happen after Biden wins and what should he do.
Emboldened by the poll prediction Neera Tanden, who was director of domestic policy for the Obama-Biden presidential campaign also said, "Biden's 'first orders of business' in office would probably be aimed at containing the death toll and addressing the economic damage."
Even if Biden pulls off a surprise now, it is clear the pollsters and pundits were far off the mark when predicting the elections once again.
Most polls are weighted surveys. That means a pollster collects a bunch of responses and then weights, or adjusts, the answers by age, gender, and political orientation so that the final count closely resembles the American electorate.
In 2016, many pollsters failed to adjust for the fact that college-educated Americans are typically more likely to respond to surveys. Another way to say this is that pollsters "under-sampled" non-college-educated voters. In short, state pollsters made a huge, obvious mistake: Their surveys failed to account for 2016's most important demographic phenomenon.
Thus, in 2020, the pollsters learning from their mistakes, changed their survey method. Pew Research Centre now weights by education within racial groups. The Marist College and NBC News/Wall Street Journal polls now also weight by geography, in part because college-educated voters are more likely to live in urban and suburban areas.
And yet the new methodology appears to have failed to rescue them once again. And 2016 and 2020 are not the only times they got things wrong.
In 1948, like Hillary and Biden, Thomas E. Dewey was the clear establishment pick from the start, and everyone dismissed the slightest idea of Harry S. Truman being the president. Even, Chicago Daliy Tribune carries the immortal headline, "Dewey Defeats Truman", Published in November 3, 1948.
In every election going back to the 1980s, the loser was, at some point, ahead in mainstream polls or in the average of polls. In the summer of 1988, Michael Dukakis led George H. W. Bush by double digits. In the spring of 1992, both Ross Perot and Bush were leading Bill Clinton. In January 1996, Bob Dole held a narrow lead over Clinton in Gallup polls. In September 2000, Al Gore surged ahead of George W. Bush. In August 2004, John Kerry led Bush. In September 2008, John McCain led Obama. In October 2012, Mitt Romney inched ahead of Obama.
Political polling was fun to watch, but given the performance of pollsters during 2016 and this years' election, it should be treated more as entertainment.