July 27, 2014
Note: Democrats hope to pick off a couple of Republican-held states, such as Georgia and Kentucky. But the YouGov results and other evidence suggest that both Mitch McConnell, the Senate minority leader from Kentucky, and David Perdue, the new Republican nominee in Georgia, should be considered favorites.
New York Times
By Nate Cohn
A deluge of cheap partisan polls has swamped a shrinking number of high-quality, nonpartisan surveys, making it hard to know who is really ahead in many political campaigns. The solution? More nonpartisan surveys.
On Sunday, the research firm YouGov, in partnership with The New York Times and CBS News, released the first wave of results from an online panel of more than 100,000 respondents nationwide, which asked them their preferences in coming elections. The results offer a trove of nonpartisan data and show a broad and competitive playing field heading into the final few months of the campaign.
The Republicans appear to hold a slight advantage in the fight for the Senate and remain in a dominant position in the House. They need to pick up six seats to gain Senate control, and they hold a clear advantage in races in three states: South Dakota, Montana and West Virginia. The data from YouGov, an opinion-research firm that enjoyed success in 2012, finds the G.O.P. with a nominal lead in five additional states.
The five states where the Republicans hold a slight lead in the YouGov panel include three Southern ones — Arkansas, Louisiana and North Carolina — where Democratic incumbents face tough re-election contests and where Mitt Romney won in 2012. Republicans also have a slight edge in Iowa and Michigan, two open seats in states that usually vote for Democrats in presidential elections.
The Republican advantage, however, is not especially significant in these states, suggesting that the campaign remains up for grabs. The results are broadly consistent with the Times’s forecasting model, which incorporates surveys, fund-raising data and other information, and currently gives the Republicans a 60 percent chance of winning the Senate.
It’s usually best to focus on polling averages that incorporate several polls rather than placing too much weight on any individual poll. Unfortunately, there have not been many high-quality polls in most of the competitive states this year. The YouGov state-by-state results nearly double the total number of nonpartisan polls in the most competitive states so far this year. In some states, today’s YouGov findings are the first from a nonpartisan firm in months.
YouGov’s work is worthy of its own discussion because it’s the first set of data from an online panel this year. The other nonpartisan surveys have used traditional, random-digit dialing to reach a sample of adults by telephone.
Random-digit dialing has long been the gold standard for public polling, but declining response rates may be complicating the ability of telephone polls to capitalize on the advantages of random sampling. Most polls underestimated President Obama’s standing in 2012, perhaps because young and nonwhite voters were least likely to own a landline and least likely to respond to telephone pollsters. Polls may also have exaggerated Mr. Romney’s gains after the first presidential debate, because Mr. Obama’s supporters were less willing to respond after his weak performance. The phenomenon is known as “differential non-response.”
As the young voters who are less likely to respond to telephone surveys become an ever-greater share of the population over time, it is probably more important for analysts to have an ensemble of surveys using diverse sampling and weighting practices.
YouGov has emerged as a part of that ensemble. It has tracked many of its respondents over months, if not years, which gives it additional variables, such as a panelist’s voting history, to try to correct for non-response. After the first 2012 debate, YouGov showed less of a swing than many other polls, and its final pre-election polls were as good as or better than many other surveys in forecasting the results.
There are still questions about the effectiveness of web panels, which can reach only the 81 percent of Americans who use the Internet. That’s worse than the 98 percent of households that can be reached by a live interview telephone survey, although it’s better than the 63.5 percent of Americans who have a landline telephone and can therefore be contacted by automated polling firms, which are prohibited by federal regulations from calling people on their cellphones.
Non-Internet users tend to be less educated, less affluent and more likely to be Hispanic or over age 65. These concerns aren’t strictly theoretical: YouGov most likely underestimated President Obama’s share of the Hispanic vote in 2012. Its final survey showed Mr. Obama with 59 percent of the Hispanic vote, far lower than the 71 percent in the exit polls.
Another issue is that the YouGov panel does not use probability sampling, the theoretical underpinning of modern polling. In a probability sample, every voter should have an equal chance of being randomly selected, making the sample representative. Phone numbers provide a device for randomization that is impossible online.
Instead, YouGov attempts to build a large, diverse panel and then match its panelists to demographically similar respondents from the American Community Survey, an extremely rigorous probability survey conducted by the Census Bureau. This step is intended to mimic probability sampling. But it can require significant assumptions about the composition of the electorate, including partisanship. These assumptions are contestable and based on varying amounts of evidence.
All of this is controversial among survey methodologists, who are vigorously debating whether a non-probability web panel should be used for survey research. At the same time, they’re also debating whether the sharp rise in non-response is undermining the advantages of probability sampling. Only 9 percent of sampled households responded to traditional telephone polls in 2012, down from 21 percent in 2006 and 36 percent in 1997, according to the Pew Research Center.
While the methodology debate rages, it’s probably best to have an eye on a diverse suite of surveys employing diverse methodologies, with the knowledge that none are perfect in an increasingly challenging era for public-opinion research.
One striking aspect of the YouGov results is that they are broadly consistent with previous data on the campaign. Republicans appear to have narrow leads in enough states to win the Senate, but only narrow leads. The Republican lead is less than two percentage points in Michigan, Iowa, Louisiana and North Carolina. In Arkansas, Tom Cotton, a Republican challenger, leads Senator Mark Pryor, the Democratic incumbent, by four points.
The panel provides its best news for Democrats in Colorado, where Mark Udall, a Democratic incumbent, has a four-point lead. That’s far better than a recent Quinnipiac poll, which showed Mr. Udall trailing by two points, but it’s about the same as a recent NBC/Marist poll, which showed Mr. Udall up by seven points among registered voters.
Republicans are also thought to have an opportunity in Alaska, another red state with a Democratic incumbent, but YouGov shows the Democratic incumbent, Mark Begich, with a surprisingly large lead against Dan Sullivan, the former Alaska attorney general who is widely considered to be his likeliest opponent. This shouldn’t be completely discounted, but it’s worth putting in context: The data for Alaska is based on only 452 respondents. The state is sparsely populated, and Internet penetration is surely lower than elsewhere in the country, making Internet-based polling challenging.
Democrats hope to pick off a couple of Republican-held states, such as Georgia and Kentucky. But the YouGov results and other evidence suggest that both Mitch McConnell, the Senate minority leader from Kentucky, and David Perdue, the new Republican nominee in Georgia, should be considered favorites.
The panel also asked respondents about their preferences in House races, and Republicans seem overwhelmingly likely to retain control. The YouGov data suggests that Republicans have leads in 240 House races; they currently hold 234 House seats. Republicans lead by at least 8 points in 220 seats, more than the 218 needed for a majority.
The panel also offers bleak news for Democrats in the competitive gubernatorial races, where Democrats are tied in Colorado and trail by at least two points in Illinois, Michigan, Florida, Wisconsin, Ohio, Connecticut, Georgia and Arkansas.
Read the full article here: http://www.nytimes.com/2014/07/28/upshot/explaining-online-panels-and-the-2014-midterms.html?_r=0