Tags: polls | polling | methodology | quinnipiac | midterms

Questionable Polls May Shock the Midterms

Questionable Polls May Shock the Midterms


By Monday, 17 September 2018 05:00 PM Current | Bio | Archive

Many believe that the polls are rigged. This unflattering brand attribute isn’t the most positive and claims of being “fair and balanced” are not exactly the case.

What is the case is that polls can have different outcomes based on either a preconceived bias, which is built into the reporting “margin of error” and that most can easily identify. There may even be a more subtle, sinister reason — when the methodology is less identifiable to even the most sophisticated poll evaluator.

When analyzing a poll there are two important issues that must be considered. First, is the poll reliable? And secondly, is it valid?

Poll reliability has to do with consistency — that is, whether the poll gets the same results when administered over and over again. Most polls are reliable, which is consistent with most data that we see in print.

The more controversial construct for skeptics and all who seek “truth in polling” is validity. Validity addresses whether the poll is measuring what it says it is measuring. With that said, consider this:

In a recent Quinnipiac University poll published on September 10, 2018, titled: “U.S. Voters Believe Anonymous Trump Charges 2-1,” their sampling along with their methods are open to debate especially by those who were trained in research design and survey construction.

Quinnipiac’s selection of poll participants was broken down in the following way: Democrats, 34 percent; Republicans, 24 percent and Independents, 33 percent. When one considers an August 1, Gallup Poll regarding party affiliation we see a significantly different outcome with Democrats having a 27 percent share; Republicans having 28 percent and Independents 43 percent respectively. This means according to the data in these two cited polls, that Democrats are over-represented by seven, not counting Republicans and Independents when using the Gallup August 1, 2018, poll as the baseline standard.

Another variable to explore in poll bias is the practice of not using registered voter lists, and then qualifying their likelihood of voting in the upcoming election. The Quinnipiac poll had respondents self-identify their political party affiliation by asking “do you consider yourself a Republican, a Democrat, an Independent, or what,” could be viewed by the “research-rigorous” as a “confound” to the data’s outcome. Here’s why.

In an Infosurv Research Insider Blog titled: “5 Reasons Why Survey Respondents Don’t Tell the Truth,” the author cites the following quote: "Ask some survey data experts and you’ll hear that up to 50 percent in any given sample will provide dishonest responses on any given survey. Ask another group of experts and the number drops to 'a small minority.'" The point is that we don’t really know the percentage of respondents who lie in surveys. So why take the chance. Just utilize a list which identifies the respondent’s political party and the issue is minimized.

Using live interviews, especially today, has limitations too. In a study titled: “Social Desirability Bias in the 2016 Presidential Election” (The Forum 14(4) • December 2016) researchers found that college students were more prone to control their public appearances and impress others by saying they were less likely to support Trump (Klar, Weber, and Krupnikov 2016). And in another study (Enns, Lagodny, and Schuldt 2017) Trump supporters did not necessarily state their opinions when asked how they would vote.

We often hear that polls are merely a “snapshot” in time on how the electorate is feeling. The question is whether a poll’s methodology and the group think of statisticians, political consultants and candidates with “horses in the race,” are analyzing these polls with a critical eye or a biased point of view. Using history to assess the future can be risky (unless you are a historian), especially if the period is atypical from the days of yore. And it’s why the polls just may be the Midterm Brand Shocker, the Blue Wave is simply “wishful thinking.” However, reducing error is always the goal of polling, especially when you have marketing and branding in mind.

Dr. John Tantillo is a marketing and branding expert, known as The Marketing Doctor. JT utilizes his doctoral skills in applied research psychology to analyze the issues and personalities of the day utilizing his marketing and branding lens. This provides his readers with additional insight needed to understand the “new normal” in politics, news, and culture. Dr. Tantillo is the OpEd writer for Political Vanguard. He is the author of "People Buy Brands, Not Companies,” and the Udemy course "Go Brand Yourself!" You can follow him on Twitter @marketingdoctor and at Facebook.com/dr.johntantillo. To read more of his reports — Click Here Now.

© 2020 Newsmax. All rights reserved.

1Like our page
Many believe that the polls are rigged. This unflattering brand attribute isn’t the most positive and claims of being “fair and balanced” are not exactly the case.
polls, polling, methodology, quinnipiac, midterms
Monday, 17 September 2018 05:00 PM
Newsmax Media, Inc.

Newsmax, Moneynews, Newsmax Health, and Independent. American. are registered trademarks of Newsmax Media, Inc. Newsmax TV, and Newsmax World are trademarks of Newsmax Media, Inc.

America's News Page
© Newsmax Media, Inc.
All Rights Reserved