When two highly regarded Florida-based firms join forces for research into voter attitudes, we have little choice but to take them and their findings seriously.
In the case of Viewpoint Florida, two of Florida’s top-tier firms – Data Targeting (Pat Bainter and co.) and Public Concepts (Randy Nielsen and Rich Johnson) – have collaborated to “study and publish opinion data … important to all Floridians.”
This week they released a poll of “likely Republican Presidential Preference Primary (PPP) voters in Florida” that was taken the evening after the now-infamous debacle known as the CNBC debate.
The most intriguing findings from the poll are of course where Bush or Rubio voters go if either drops out.
But we’re not here to talk about that … we are analyzing the methodology of the poll and applying our saltshaker test.
Let’s establish up front that we are not huge fans of “interactive voice response” (IVR) technology in voter polls, except when it comes to a simple horse race, which this appears to be.
For these kinds of surveys, there are some technical problems with ensuring the actual voter you are looking for is the one actually taking the call. It is tough, if not impossible, to include a good sample of respondents who only own/use cell phones.
In this case, Viewpoint chose not to interview people on cell phones. That is a concern. For a GOP Primary, lack of cell phones may be less concerning than a General Election poll, but it is a concern nonetheless.
To be clear, our concerns are not for what appears the primary purpose of the survey, which is to see where, for example, Bush supporters may go if he drops out. That movement is measurable within the sample, so you can comfortably conclude – as they did that when Bush’s name is excluded – certain percentages move to either Trump or Rubio.
Concerns come when you try to “externally validate” these findings and suggest that this is a statistically valid sample of the likely GOP PPP electorate.
As the current trending is for pollsters to ensure that as many as 20 percent or 25 percent of calls are conducted via cellphone – because of the rising number of voters who no longer own or use landlines – we must recognize that this important part of the electorate was not part of the Viewpoint survey.
And that matters.
It matters because numerous studies show that cellphone respondents are different from those who still own (and frequently use) landlines. Those people are different in ways that can no longer be compensated by a good sampling of younger voters (and, no surprise, this poll skews a little older than the 2012 PPP electorate.)
And, for our purposes, it requires us to add a grain of salt.
As for measuring the impact of the debate, many would argue that “the night after” was simply not enough time to judge fallout. Usually, it takes a few days after a debate for the media to weigh in, for social media to run its course and for the proverbial water cooler conversations to take hold.
But as Viewpoint explicitly noted, “Our survey sought to capture where the field stood in the first hours after the widely-watched campaign event.” Based on that, we have absolutely no problem there.
The poll was taken of likely GOP voters (good), had a robust number (2,047) of respondents (very good) and was fairly well balanced and looked like the 2012 Republican presidential preference primary electorate (as noted above, the sample was slightly older than that electorate). And while nobody can be sure of what the electorate will actually look like this coming March, the methodology used by Viewpoint is as good as one could want.
Overall, this is a very good poll with an interesting assessment of where voters go if either Bush or Rubio drop out. But because there were no cellphone respondents, take the findings with a lone grain of salt.
Key for the Salt Shaker test:
- No salt needed: Solid pollster, solid methodology, and the sample appears to be nicely balanced.
- A grain of salt: The poll has one or two non-critical problems and should be taken with a grain of salt.
- A few grains: There are several concerns with how the poll was conducted, but not enough to throw it out entirely.
- A half shaker: There are enough problems with the methodology to warrant serious concerns, and the poll should not be taken seriously.
- A full shaker: The poll has so many problems it should not only be completely disregarded but pollsters receiving multiple “full shakers” will no longer have their polls covered byFlorida Politics/SaintPetersBlog.
Steven J. Vancore is the president of Clearview Research. With a master’s degree in Marketing Communications from Florida State University, he has nearly 30 years’ experience conducting polls and focus groups throughout the state. He serves as an adjunct instructor in the Masters of Applied American Policy and Politics program at FSU. He can be reached at email@example.com.