Saturday, September 29, 2012

Party Affiliation, Skewing Polls, and Voting

When one party endures a seemingly unending streak of disappointing polls, it is natural to begin asking if there could be some reason why the pollsters are all in error. Recent presidential election polling has showed results heavily tilted toward the Democratic candidate. This has prompted a few on the Republican side to claim the polls are in error because they are not sampling enough Republican voters. There is even an attempt to recalibrate polls using the "correct" ratio of Republicans to Democrats. This nonsense leads nowhere, but it did prompt the Pew Research Center to issue an interesting article summarizing the issues associated with polling and party affiliation.
"While all of our surveys are statistically adjusted to represent the proper proportion of Americans in different regions of the country; younger and older Americans; whites, African Americans and Hispanics; and even the correct share of adults who rely on cell phones as opposed to landline phones, these are all known, and relatively stable, characteristics of the population that can be verified off of U.S. Census Bureau data or other high quality government data sources."

"Party identification is another thing entirely. Most fundamentally, it is an attitude, not a demographic. To put it simply, party identification is one of the aspects of public opinion that our surveys are trying to measure, not something that we know ahead of time...."

To make the point that party affiliation changes continually, Pew provided this chart of recent polling data:





Some have argued that the exit poll data from the previous election might be more accurate in determining the appropriate mix of voters to consider. Pew points out that data that is at least two years old has to be suspect in terms of accuracy. The article provides these results from exit polling of recent elections:



Note that voters present a higher level of Republican participation than would be expected from the party’s representation among all those registered to vote. It turns out that Republicans are more likely to vote than those who claim to be Democrats or Democrat leaning. In a presidential election year only about 60% of registered voters actually take the time to vote. In an off-year election the number is even lower. This puts a lot of pressure on the poll takers to determine the people who can be depended upon to vote: the "likely voter."

"But, in the same way that party affiliation is not fixed for a given individual, being a "likely voter" is not a demographic characteristic like gender or race. Political campaigns are, in part, designed to mobilize supporters to vote. Although it may feel like the presidential campaign is in full swing, much of the hard work of mobilizing voters has not yet taken place and won’t occur until much closer to the election. Accordingly, any determination of who is a likely voter today – three months before the election – is apt to contain a significant amount of error. For this reason, Pew Research and many other polling organizations typically do not report on likely voters until September, after the nominating conventions have concluded and the campaign is fully underway."

To illustrate the importance of this likely voter model, Pew provides this data:



"In these polls the vote margin has been, on average, five points more favorable to the Republican candidates when based on likely voters rather than registered voters. These final estimates of the outcome have generally been very accurate, especially when undecided respondents are allocated to the candidates."

While the Republicans seem to have more-dedicated voters, there seems to be a long-term trend towards fewer of them, or, at least, fewer who choose to admit to being a Republican.



This recent trend is partly driven by concurrent events, but it also represents long-term demographic changes that are more favorable to the Democrats.

No comments:

Post a Comment