Polling Matters by Frank Newport

Author:Frank Newport [NEWPORT, FRANK]
Language: eng
Format: epub
Tags: BUS000000
ISBN: 9780759511767
Publisher: Grand Central Publishing
Published: 2004-07-30T00:00:00+00:00

THE CONGRESSIONAL VOTER, NOVEMBER 5, 2002

Political Party Affiliation of Candidates Random Sample of 715 Likely Voters Interviewed October 31-November 3 Actual Voting Affiliation of More Than 75 Million Voters on Election Day, November 5*

Republican 51% 51.7%

Democrat 45% 45%

*Based on totals as of November 7, 2002.

This whole process is a refinement of something that has been going on for more than sixty-five years. Back in 1936, a young Iowan, George Gallup, startled the world when he declared that Franklin D. Roosevelt was going to be reelected as president of the United States. Gallup based that prediction on a small sample of only several thousand people. At the same time, the Literary Digest magazine had a group of several million people in its famous poll that had been running for a number of years. The Literary Digest said Roosevelt would go down to defeat. The Digest’s editors laughed at Gallup. How could this man’s small group of people possibly be as accurate as the magazine’s own huge sample? Gallup stuck to his guns. His predictions were published before the election in the Washington Post and many other newspapers. A major showdown was in place.

Gallup had a secret weapon. His polling provided what he called “the first real test of scientific sampling in a national election.” 4 The Digest’s sample, although massive, was essentially a convenience sample—based on gathering people’s names and addresses from subscription, telephone, and automobile registration lists. It made no pretense of following any type of scientific sampling procedures.

Gallup’s theory of sampling won the day. Roosevelt won the election (and two more after that). The Literary Digest sputtered, but couldn’t explain away its miscall. Coincidentally, a few years later it folded. Gallup, on the other hand, is still very much with us, and George Gallup’s basic principles of sampling are still the basis for ours and almost all modern-day polls. There are a host of new complications that we face today, and many procedures we use are significantly improved over those used by George Gallup in the 1930s. But, as we saw in the November 2002 midterm elections, when sampled and mea-sured accurately, the opinions of just a small number of Americans can and do accurately represent the opinions and actual behavior of millions.

It’s not just this one election. Most preelection polls end up providing accurate predictions of the actual election results. The National Council on Public Polls has compiled lists of polls and compared them to the outcome results across a number of elections in recent years, and has concluded that they indeed do an accurate job of sampling, as validated by the close correlation between the results of the sampling and the actual vote on election day.

Despite all of this evidence, though, there is no way around the fact that many skeptics don’t believe that polling small numbers of people can accurately represent the views of millions. Yet it does. How does this process work?

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.