Oversampling Is Not A Nefarious Democratic Plot

It's a technique commonly used by pollsters -- including Trump's campaign manager.
Republican U.S. presidential nominee Donald Trump speaks during a rally in St. Augustine, Florida, on Monday.
Republican U.S. presidential nominee Donald Trump speaks during a rally in St. Augustine, Florida, on Monday.
Jonathan Ernst/Reuters

Donald Trump’s campaign has highlighted some of the finer, typically ignored points of polling this year, usually by boisterously misunderstanding them.

“WikiLeaks also shows how John Podesta rigged the polls by oversampling Democrats ― a voter suppression technique,” the GOP presidential nominee told voters during a Florida rally on Monday.

Trump’s claim appears to be loosely based on a leaked 2008 email from a Democratic activist, which, as The Washington Post reported earlier Monday, includes an enjoinder to “oversample” certain generally Democratic-leaning subgroups including racial minorities and younger voters.

Trump supporters, apparently, read this as an instruction to ensure that polls were purposely skewed to include extra Democrats.

Oversampling, though, isn’t about overstating the size of one group relative to others ― it’s about making sure the results for that group are as accurate as possible.

Often, pollsters are looking to get a better picture of a group that ordinarily comprises only a small fraction of survey-takers. They’ll make an effort to find extra people in that group, raising the sample size and allowing them to better measure what that slice of the population thinks. Crucially, though, oversampling doesn’t change the weight that any subgroup is given in the poll overall.

As the pollsters at Pew Research explain in their extensive FAQ:

For some surveys, it is important to ensure that there are enough members of a certain subgroup in the population so that more reliable estimates can be reported for that group. To do this, we oversample members of the subgroup by selecting more people from this group than would typically be done if everyone in the sample had an equal chance of being selected. Because the margin of sampling error is related to the size of the sample, increasing the sample size for a particular subgroup through the use of oversampling allows for estimates to be made with a smaller margin of error. A survey that includes an oversample weights the results so that members in the oversampled group are weighted to their actual proportion in the population; this allows for the overall survey results to represent both the national population and the oversampled subgroup.

Since African-Americans make up about 13.6 percent of the population, for instance, a poll of 1,000 people would typically include only about 136 African-Americans. The margin of sampling error for African-Americans’ opinions in that case, per Pew, would be somewhere around 10.5 percentage points.

So, pollsters interested in focusing on African-Americans’ views might oversample them as a group, conducting another couple of hundred interviews to bring up their sample size and lower the margin of error, offering more reliable information. The poll would still be weighted, however, so that African-Americans would account for the same 13.6 percent of the national population.

Oversampling, while useful, is expensive, which would make it a particularly baffling and ineffective way of biasing the polls.

“If you wanted to just bias the poll, you wouldn’t waste the extra money making all these extra calls ― you’d try to manipulate it from the beginning,” Republican pollster Jon McHenry told The Atlantic. “This is an added expense to the pollster with the idea of getting more information about a certain subgroup, and weighting that back so you understand the overall as well.”

Don’t take our word for it, though ― or Pew’s or McHenry’s. We’ve also pulled up some real-world examples of when oversampling might come in handy, courtesy of Trump’s campaign manager, Kellyanne Conway.

Here, for instance, is a 2013 poll of the New York City mayoral race from Conway’s firm, The Polling Company, Inc./WomanTrend. The survey, conducted on behalf of the city’s police commissioner, oversampled Republicans to get a better sense of his chances in the party primary.

The Polling Company, Inc./WomanTrend

Here’s another poll conducted in part by Conway’s firm, which oversamples African-American women, Latinas, Asian/Pacific Islander women and Native American women.

YWCA

And here’s Conway’s firm oversampling young, black and Hispanic voters for a poll on behalf of the conservative advocacy group FreedomWorks.

FreedomWorks

Editor’s note: Donald Trump regularlyincitespolitical violence and is a

Popular in the Community

Close

What's Hot