Tag Archives: polls

The real margin of error for polls

In my daily scanning of the news, looking for stories that are both educational as well as entertaining, I came across this particular post: “WATCH – This Viral Video Perfectly Illustrates Why Americans Don’t Trust the Lamestream Media”.

The title is typical click-bait, hinting at something truly revealing that nine times out of ten turns out to be immensely disappointing. This time, however, I found that the post revealed a lie about political polls, almost as an aside, that is simply never noted.

The video itself is entertaining. It shows one particularly bad performance by a MSNBC political reporter, where in only about five minutes he used NBC polls to make a string of predictions about the presidential election, every single one of which turned out to be spectacularly wrong. I’ve embedded the video below the fold for your enjoyment.

What the post however noted that I found revealing was something else:

After all, these were NBC polls that Kornacki cited time and time again. Polls that showed Hillary Clinton leading Donald Trump in places like North Carolina, Georgia, and Ohio. The polls were terribly off-base. In some cases, the NBC numbers showed Clinton with a double-digit lead in states that she went on to lose. In other words, the polls were not by any means scientific, fair, or truthful.

Does the phrase “margin of error” ring a bell? Typically, it is between three and four percent, in order to be deemed usable, anyway. But NBC’s margin of error in Pennsylvania was 11 percent. [emphasis mine]

In the past decade or so political polls have routinely included what they call their “margin of error,” which generally for most polls ranges, as noted above, about three to four percent. This number is, and has always been a lie, however, as shown by the highlighted text. The real margin of error is the difference between what the poll predicted and what the actual results were. And for all of these NBC polls, the margin of error was not 3 to 4 percent, but anywhere from 11 to 30 percent!

In other words, these polls were worthless. Worse, they suggest some intentional manipulation, as they all made their error in only one direction (against Trump and for Clinton), much like the tampered global temperature data that we see coming from NASA and NOAA. It could be that there is confirmation bias going on here, producing results these liberal news outlets wish, but I do not think so. NBC, and its sister station MSNBC, have repeatedly in the past five years committed some egregious journalist frauds, all of which designed to make conservatives and Republicans look bad and to promote the interests of the Democratic Party. The network has made no moves to correct the problems. Nor has it fired anyone.

I think it very reasonable to suspect intentional fraud here, specifically aimed at helping the Democrats.

More important, this story illustrates why we should all laugh uproariously the next time we see a mainstream media journalist note pompously that the poll he or she is citing has a margin of error of 3%. He or she either doesn’t know what they are talking about, or they know very well and think you are too stupid to notice.
» Read more

Why the polls underestimate Tuesday’s Republican sweep

The answer is very simple, at least according to this particular pollster:

The American people cannot stand Barack Obama. They dislike his policies. They dislike his “above it all” demeanor. And they rose out of their chairs and off their couches and came out in droves to defeat anyone who they thought was even remotely supportive of him or his administration.

Yep, I was one of those dumb pollster/analysts who thought that no president in a midterm election could possibly be as big of a drag on candidates as was Obama. But I was wrong. He wasn’t just a drag; he was his own voter turnout machine for Republicans.

How could this be? How could the voters be so blind? Don’t they realize that Barack Obama cares!?

Obamacare poll numbers crash

Finding out what’s in it: New polls show that the more the public becomes familiar with Obamacare, the more they hate it.

Hey, what’s not to like? Obamacare gives you higher premiums, less availability of doctors, less insurance coverage, more bureaucracy, more paperwork, and — best of all! — increased government interference in your life.

The absurd oversampling of Democrats in most recent polls, as illustrated in one graph.

The absurd oversampling of Democrats in most recent polls, as illustrated in one graph.

There is no reasonable justification for this Democratic skew, especially those greater than five percent, unless you want to make it look like Obama is in the lead.

The just released Pew poll which shows Obama with a 10 point lead oversampled Democrats by 19 points.

Here we go again: The just released Pew poll which shows Obama with a 10 point lead oversampled Democrats by 19 points!

This is disgraceful work, and should discredit Pew as a pollster. There is no chance in hell that Democrats are going to outvote Republicans by 19 points come November. They didn’t even do that in 2008, when Obama won handily. For Pew to release a poll with a sampling that badly skewed smacks of incompetence, fraud, political manipulation, or a willingness to deny reality.

Much has been made in the past few days of this NYT/CBS poll that found the Presidential race to be a dead heat.

Oversampling Democrats: Much has been made in the past few days of this NYT/CBS poll that found the Presidential race to be a dead heat. This article however is the first I’ve found that notes this key fact about the poll:

Among registered voters, the NYT/CBS poll also oversamples Democrats and Independents: D-33/R-27/I-41. There’s no way the 2012 electorate will only be made up of 27% Republicans.

That’s right, this NYT/CBS poll purposely skewed the results by polling 6% more Democrats than Republicans. In other words, the race is likely not such a dead heat. Obama is significantly behind, especially since all polls have consistently found that voting enthusiasm is far higher among Republicans than Democrats.

Why the Presidential race looks so close: Too many pollsters are oversampling Democrats.

Why the Presidential race looks so close: Too many pollsters are oversampling Democrats.

An honest poll would reflect the actual split of Democrats to Republicans. Instead, pollsters seem to repeatedly assume there are many more Democrats in the country than there actually are, which falsely skews the results to Obama’s favor.

The thing is, this oversampling will do the Democrats no good this coming election. It gives them the false impression that they are doing better than they are, which means they will not do what they should to make up ground. Moreover, too many people today are aware of this biased polling, and thus less influenced by them.

Finally, and most important, these biased polls illustrate a fundamental unwillingness of many on the left to recognize the country’s real political state. These leftwing pollsters reflect the attitude of many Democrats, who refuse to believe the majority of the county opposes their policies, even when the 2010 elections should have told them different. They are in denial, and when November comes they are going to be very surprised by the results.

Obamacare: 0-98

Obamacare: 0-98

As the nation awaits the Supreme Court’s ruling on President Obama’s centerpiece legislation, it’s worth reviewing the American public’s response to it across the 27 months since Obama signed it into law. Over that span, from March 2010 through a poll released this morning, Rasmussen has conducted 98 polls of likely voters. All 98 times, support for repeal has outpaced opposition to repeal. Across 98 contests, Obamacare has gone 0 and 98.

What amazes me is how completely oblivious the Democratic Party has been to these polls. Despite the public’s clear and passionate opposition to this law the Democrats have continued to act as if they believe the law will win them votes.

Poll numbers suggest largest Republican victory in generations

Gallup poll numbers suggest tomorrow’s Republican victory could be the largest in generations, and could exceed all predictions. Key quote:

It should be noted, however, that this year’s 15-point gap in favor of the Republican candidates among likely voters is unprecedented in Gallup polling and could result in the largest Republican margin in House voting in several generations. This means that seat projections have moved into uncharted territory, in which past relationships between the national two-party vote and the number of seats won may not be maintained. [emphasis mine]

Toronto elects conservative mayor by a surprising margin

Is this a hint of what’s to come on Tuesday? Toronto yesterday not only elected a conservative mayor by a very large margin, four incumbent councillors were also defeated soundly. Key quote:

Polls, indicating the race was razor edge close, were proven false in 11 single minutes! . . . [The conservative] Ford won with 383,501 votes—more than the votes of his two main opponents combined.

Gallup’s astonishing numbers

I can see November from my house. New numbers from Gallup are “astonishing.” To quote Michael Barone today in the Washington Examiner: “These two numbers, if translated into popular votes in the 435 congressional districts, suggest huge gains for Republicans and a Republican House majority the likes of which we have not seen since the election cycles of 1946 or even 1928.”

Something’s coming, something good

Three polls issued today make it very clear that the upcoming November elections are going to be a very different animal than any election anyone has seen in decades.

First, Public Policy Polling (PPP) finds that in the West Virginia race for the Senate seat formerly held by Robert Byrd, long shot Republican John Raese is leading shoe-in Democrat Joe Manchin by 3 points.

Second, Rasmussen finds that not only is Republican Joe Miller leading his opponents in the Alaska Senate race by 15%, the Democrat candidate, Scott McAdams, can only garner 25%. Meanwhile, Lisa Murkowski, who lost to Miller in a primary upset, is doing almost as bad as an independent write-in candidate, with 27%.

Third, a Quinnipiac poll shows Republican Tom Corbett destroying Democrat Dan Onorato by a 54-39 margin in the race for Pennsylvania governor.

Not only do these numbers show a willingness of the public to consider new and unknown candidates and reject incumbents, they also show a surprising hostility to Democrat candidates in regions that have always been considered Democrat strongholds. In West Virginia, the accepted wisdom was that the Democrat Manchin would be nominated and then annointed. Not so. In Alaska, not only did Miller upset the incumbent Murkowski in the Republican primary, voters apparently have little interest in seeing her return to office, or give her Democrat rival the job either. And in Pennsylvania, a swing state that has in recent years been swinging increasingly Democratic, the numbers show instead a complete reversal of that trend and a total rejection of the Democrat candidate.

Yes, November 2nd is going to be an interesting day indeed.

Update: Another poll released today from PPP and commissioned by the leftwing website, Daily Kos, continues these astonishing trends. In the Wisconsin Senate race, Democrat incumbent Russ Feingold now trails Republican Ron Johnson by 11% points. And in Wisconsin governor’s race, the same poll found the Republican leading by 9%.

Republicans lead by 10 in Gallup generic poll

Still doubt the magnitude of the turnover expected in the November 2010 election? Then consider Gallup’s most recent generic poll, which has the Republicans now up by 10 points, the most in history. Key quote:

The Republican leads of 6, 7, and 10 points this month are all higher than any previous midterm Republican advantage in Gallup’s history of tracking the generic ballot, which dates to 1942. Prior to this year, the highest such gap was five points, measured in June 2002 and July 1994. Elections in both of these years resulted in significant Republican gains in House seats.