September 28, 2014

Today gives us an opportunity to explore polling once again.

Results from a Rasmussen poll have been reported. They report that Raimondo is up over Fung by five points. The poll was taken of 750 likely voters over the period of September 23-25. The margin of error was +/- 4% and there was a confidence level of 95%.

What does it all mean? Consider the following before making a determination. The question asked by the pollster was: “If the election for governor of Rhode Island were held today, would you vote for Republican Allan Fung or Democrat Gina Raimondo?”

You can immediately see the problem with this poll, the problem of inclusion. If you were at a party and you were asked whether you wanted grape or orange soda would you choose cola? This poll question is pretty flawed poll from the start (especially when over 10% went out of their way to say they preferred another candidate).

If I were the pollster and wanted greater accuracy I would have added the name of the third candidate and get results, but, I assume they were too deep into their polling to make such an immediate adjustment.

Most stand up reporters are clearly making note of the omission of Healey. The Providence Journal, in reporting it, put it in the back pages of the paper and Alex Kaufman clearly indicated that Healey was not included.

I personally would not trust this Rasmussen poll as reported, but the poll itself is not completely worthless if one examines what it doesn’t say as opposed to what it does.

Take a good look at the reporting. Despite being offered only a choice of two people, over ten percent indicated they preferred another candidate. Think about it for just a second. They did not report they were undecided, of which there are 11%. They reported that a full 11% were voting for another unnamed and unmentioned candidate.

Take heart in this statistic. If people were offered the third choice by name, the probable outcome would show an even greater level of support. It is for this reason I feel that we are making in-roads that cannot be ignored.

Having 11% of the people volunteering a third name is quite encouraging. It is not enough to celebrate, but it is a very positive sign in that many people simply answer what is asked.

Go by your gut and be realistic. The people on the streets seem far more enthusiastic about the campaign. Winning yet? Hardly, but very much in the fight.

Listen to reporting of the poll and work to correct incorrect assumptions that might occur in reporting. In this, never, never, never over-assert your position, just call attention to the flaws in the data.

It is very good if the opponent tries to make hay with the skewed poll. If they do it vociferously, then you should smell that blood is in the air.

While you may think this is worth just letting it run its news cycle, that strategy would be more likely a good one if the news was all bad. The high number of those challenging the question by stating a third candidate makes this worthy of ignoring the traditional path.

Challenging a poll with such a false premise is easy. Be careful when you are faced with a better posed polling question. While third parties and independents will poll with greater consistency with the poll’s margin of error, in either direction, it is well too early to consider the battle won or lost.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s