Quinnipiac’s latest poll is a good one, but with a slight methodology problem that could favor Donald Trump.
What did the poll find?
It found Trump nearly lapping what is left of the field and is 16-points ahead of the second closest candidate, Marco Rubio. If accurate (and we know the race will change between now and March 15); this could spell serious trouble for anyone hoping to challenge the front-runner.
Let’s break out the salt shaker and evaluate their latest offering:
- Large enough sample: 700 voters. Check.
- Balanced according to known and measurable demographics. Check.
- Calls are taken by landline AND cell phones. Check.
- Live callers and options for bilingual respondents. Check and check.
These are all crucial; good for Q-Pac for being so diligent.
But there is one small problem and this problem could benefit the front-runner.
From the methodology, it is unclear how Quinnipiac chose the respondents. Their method says they interviewed “likely Florida Republican primary voters” but indicate they were found by a “Random Digit Dialing” (RDD) system.
In speaking with the pollster, he said respondents self-identified as “likely voting Republicans.”
The issue is summed up in one word: “self-identified.”
That is somewhat problematic on two fronts.
First, people who are not registered to vote could partake in the poll if they merely claim to the pollster that they are Republicans. Think about the nonregistered Trump supporter who gets a call and wants to show the world how much he loves the Donald.
Second, non-likely voters could claim (as most respondents do) that they are likely to vote. So even if the respondent is a Republican (and tells the truth in that regard) he or she is highly probable to exaggerate past voting frequency. We find in our polls that when we ask this question, greater than 90 percent of voters who take a poll claim that they vote “in nearly every election.” We know this claim to not be true. If it were true, we wouldn’t be looking at a statewide average in the neighborhood of 20 percent turnout in primary elections. This kind of response is what is known as “socially desirable response patterning” where voters say what they think they are supposed to say … “Oh yes sir, I never miss an election.”
So how does that favor Trump?
Most analyses we have examined said Trump does better among nonvoters or non-frequent voters. If this is the case — and we do not claim that it is — then this sample could have oversampled those who are not likely to vote in the March 15 primary. And, this does seem to be the case, as the methodology shows 26 percent of respondents are between ages 18 and 44; a number that is skewed closer to registered Republicans of that age group (28 percent) than their likely PPP voting counterparts (16 percent).
For the Trump haters out there, however, don’t get your hopes up too high. This factor could — could — influence the findings but won’t change the conclusions that much. Our best (educated) guess is that the impact would be in the low single digits and as this poll shows Trump with a substantial 16-point lead, it is hard to imagine that running these respondents through the voter file would change that a great deal.
But, it still requires us to take this poll with a grain — just a 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 noncritical 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 by FloridaPolitics.com/SaintPetersBlog.
Steven J. Vancore is the president of Clearview Research. 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 and can be reached at firstname.lastname@example.org.