Most people probably wouldn’t know who Nate Silver was if he showed up on their doorsteps, but among numbers geeks, especially statisticians, he’s the male equivalent of Kim Kardashian.

Silver is the author of the best-selling 2012 book, “The Signal and the Noise: Why So Many Predictions Fail — But Some Don’t.” In it, he analyzes predictions about everything from baseball to weather forecasting to earthquakes to polling. (Being a polling geek, that was the section I liked the best.)

His FiveThirtyEight.com blog ranks among the top sites for number-crunchers, and Time magazine ranked him as one of the world’s “100 Most Influential People.”

But when he tried to predict the recent election in Great Britain, he was pathetically off the mark. His website said the chance that incumbent Prime Minister David Cameron’s Conservatives would win a majority of seats “was vanishingly small when the polls closed — around 1 in 500.”

Yet, when the votes were counted, the Tories had notched 331 seats in Parliament to Labor’s 232. That meant Cameron’s party didn’t need to form a coalition with any rivals, giving Conservatives the liberty to pass any legislation they wanted.

In a post-election column, Silver said this wasn’t the first time polls had missed an important vote recently. Besides the May 7 British vote, he listed three others:

• The independence vote in Scotland last September that polls said would be close, within 2 percent or 3 percent. In fact, voters rejected it by 11 points.

• November’s U.S. Senate races, which Republicans were predicted to win, they did — but by average margins a full 4 percent higher than the polls had forecast.

• And in Israel in March, polls had Prime Minister Benjamin Netanyahu’s Likud party winning just 22 seats in the Knesset, but it actually prevailed in 30, giving him a hard-won victory.

“Perhaps it’s just been a run of bad luck,” Silver noted. “But there are lots of reasons to worry about the state of the polling industry. Voters are becoming harder to contact, especially on landline telephones. Online polls have become commonplace, but some eschew probability sampling (reaching groups according to their percentage of the population), historically the bedrock of polling methodology.”

And sometimes pollsters put a thumb on the scale: “In the U.S., some pollsters have been caught withholding results when they differ from other surveys (my italics), ‘herding’ toward a false consensus about a race instead of behaving independently.”

Why would pollsters “herd” results? Because, as John Fund wrote on www.nationalreview.com on May 10, they fear that if their polls are too far out of line with the majority, they will lose credibility.

However, sometimes the “outlier” poll is the accurate one, and keeping it secret may affect the outcome of an election — perhaps by concealing a late surge by a challenger, as happened in the Virginia Senate race last year.

As Fund notes, polls also may be skewed because many conservatives are reluctant to give accurate answers to pollsters’ questions, or dodge replying altogether.

That’s because they are convinced that the national media — which to them includes polling firms — are biased against their views and would ridicule or criticize them for holding them.

But inside a voting booth, they cast their ballots for conservative causes and candidates.

Fund says, “Pollsters in Britain have long realized the potential polling problem created by the ‘shy Tory’ vote — referring to those voters who don’t want to admit to pollsters that they are going against the grain of media coverage and might cast a politically incorrect vote.”

Are the shy Tories — and any “shy Republicans” over here — correct about that? Kirsten Powers, a widely published columnist who is a lifelong Democrat and former Clinton administration official, has just authored a new book called “The Silencing” that says they are.

She writes, “The illiberal left isn’t just ruining reputations and lives with their campaigns of delegitimization and disparagement. They are harming all of society by silencing important debates, denying people the right to draw their own conclusions, and derailing reporting and research that is important to our understanding of the world. They are robbing culture of the diversity of thought that is so central to learning and discovery.”

As Powers notes, “When people are afraid to express their opinions because they’ve seen other people treated as deviants deserving of public shaming or worse, they will be less likely to speak freely. This already happens in newsrooms and academia, where people hide their religious or political views in water cooler conversation for fear of discrimination, or ultimately just opt out of the hostile work environments altogether.”

So when leftists are surprised that some elections don’t come out the way they expected or desired, it appears they have only themselves to blame.

M.D. Harmon, a retired journalist and military officer, is a freelance writer and speaker. Email at: [email protected].


Only subscribers are eligible to post comments. Please subscribe or to participate in the conversation. Here’s why.

Use the form below to reset your password. When you've submitted your account email, we will send an email with a reset code.

filed under: