close
close

Association-anemone

Bite-sized brilliance in every update

Understanding Surveys: What you need to know about margin of error, methods and more
asane

Understanding Surveys: What you need to know about margin of error, methods and more

While the Americans wait choice results, many look at POLLS for answers.

JUMP TO: MARGIN OF ERROR it PHONE/DIGITAL it EXTERNAL SURVEYS

Dr. Andy Smith of the University of New Hampshire Survey Center joined LiveNOW from FOX on election day with tips for deciphering POLLSand how to understand them better.

The margin of error describes how close the result of a survey can reasonably be to being truly representative of the entire population. In other words, even the purest random sampling of surveyors will not be an exact match of the entire American population.

The calculation of the margin of error works through a complicated mathematical theory known as the central limit theorem, Smith said. But he gave some tips to make it easier to understand.

He said the biggest confusion about sampling error is that people think it applies to the percentage gap between candidates, which is not the case.

Who is currently leading in the polls?

“What you have to do is apply a margin of sampling error to both estimates,” he said. “So Donald Trump at 46%, in this example (with a 3% margin of error), could be as high as 49%; it could be up to 43%; Harris at 50%, it could be up to 47% or up to 53%.”

“You really have to double the margin of sampling error if you want to understand whether the difference between the two candidates is statistically significant,” he added.

“The survey industry is going through what I would call a paradigm shift, where we’re moving from the types of methods that worked 30, 40 years ago and don’t really work anymore,” Smith said.

He said response rates to phone interviews have dropped significantly in recent years, to the point where he said only about 5 percent of people who are contacted for phone surveys actually complete them.

“This results in very, very expensive telephone surveys and, (as we saw in) 2016, inaccurate telephone surveys,” he said.

He said that more polls are being conducted digitally in this election, but that there are also some different methodologies for digital methods.

“We’re going to see after this election a little bit of research to understand which of the methodologies that were used actually had the best results and we’re going to use that knowledge going forward,” he said.

“I’m very cautious about saying one poll is better than another at this point, because frankly, we just don’t know. We are in the middle of this development of best practices and we are not yet at the end of it. .”

Every election cycle, a few polls publish shocking results that attract significant attention.

The most recent was very anticipated POLL from J. Ann Selzer, the “gold standard” Iowa poll showing Kamala Harris beating Donald Trump by 3 points in the Hawkeye State.

So how do poll results vary so widely?

Smith says that could have to do with how the survey was conducted or that an unusual sampling group was used that could have excluded a certain demographic.