Analyzing the CNN poll showing the governor’s race deadlocked – A grain of salt

in Uncategorized by

The players seem to change daily with new pollsters popping up left and right. The methods seem to vary slightly with some using blended samples, some just phones, and some relying on an all-electronic means.

While the players change and the methods vary, the narrative is seemingly settling in to a “too close to call” storyline.

The latest from CNN and “ORC International” is no exception as they have the race between Crist and Scott tied at 44% each.

ORC International, seems like a big and serious company. But big and serious doesn’t necessarily mean they understand Florida politics and, likewise, political polling in the Sunshine State.

While they polled the too broad category of “adults,” they were kind enough to let us look behind the curtain a bit and get top lines from what they describe as “likely voters.”

Unfortunately, we don’t know the makeup of these so-called likely voters. We know they balanced the survey on Census data (really?) and that about one third  “described themselves” as Democrats, Independents and Republicans respectively.

Again, that is among all adults – and may not be reflective of the “likely voters.”

Secondly, it would have been nice to know the makeup of what the respondents actually are and not as they wish themselves to be – that would have been a more accurate way to properly balance this sample.  (I mean if you asked me, I would say I was 6’2”, stunningly good-looking and 185 pounds. But since I am not Nick Iarossi, they would need to categorize me differently – and code me as I actually am.)  Likewise, their propensity to vote was not based on the respondent’s actual voter history but how they described themselves in the poll.

The pollster does get super-kudos for putting in separate margin of error calculations under each table and are the first I have seen do that this year – that is the correct way to measure M.O.E. – so good for them.

But in the end, we really do not know the balance of this poll by party (how many actual Democrats versus Republicans) and if these are actually likely voters.   Further, we do not know if cell phones were included in the sample as the methodology statement is silent on the subject.

Verdict: Take this poll with a grain of salt.

What is the SPB Salt Shaker Scale? It’s our new measurement guide to reading polls. These are the ratings:

  • A full shaker: There are enough problems with the methodology to warrant serious concerns.
  • A few grains: There are some concerns with how this poll was conducted and/or with the Demographic make-up to raise some issues.
  • A single grain: There are only a few concerns with how the poll was conducted.
  • No salt needed: Solid pollster, solid methodology and the numbers look balanced.

Peter Schorsch is the President of Extensive Enterprises and is the publisher of some of Florida’s most influential new media websites, including SaintPetersBlog.com, FloridaPolitics.com, ContextFlorida.com, and Sunburn, the morning read of what’s hot in Florida politics. SaintPetersBlog has for three years running been ranked by the Washington Post as the best state-based blog in Florida. In addition to his publishing efforts, Peter is a political consultant to several of the state’s largest governmental affairs and public relations firms. Peter lives in St. Petersburg with his wife, Michelle, and their daughter, Ella.