When is a poll just a poll?

I got a call from a reporter yesterday who wanted to talk about the new Elon poll that shows McCrory up three in the NC Governor’s race.  I didn’t’ give her what she wanted as I said that until I saw more polls like this, I was still sticking with the RCP average which shows McCrory clearly down. (Down an average of 3.6 in the latest, and even more if you don’t include the Civitas poll– and I’m always skeptical of their polls).  Elon does a solid poll (uses humans to call landlines and cell phones), but sometimes results just don’t pass the smell test.

#1) Is there anything in the real world that would actually explain McCrory gaining significantly in the polls in the past couple weeks?!  Especially with the NCAA and ACC pulling out of NC?  Ummm, nope.  So, maybe the older polls are systematically under-estimating McCrory, but I sure as hell doubt there’s been actual movement towards him among the NC electorate.

#2) Even more notably, McCrory is way outperforming the Republican Senator, Richard Burr, who is down 1 in the same poll to his Democratic challenger.  Given my knowledge of NC politics and Political Science, I just have a hard time envisioning a reality where McCrory is actually up 3 and Burr down 1.  Going with my instincts and knowledge over a poll of <700 voters on this one.  I asked my class yesterday if they could create a plausible explanation for that pattern of results.  None even tried.  Nate Cohn noticed this as well.

So, again, not to pick on Elon.  Sometimes you do everything right and the results are still funny.  But there’s times when we need to put a poll in broader context and use some common sense and I really think this is one of those times.

Advertisements

About Steve Greene
Professor of Political Science at NC State http://faculty.chass.ncsu.edu/shgreene

One Response to When is a poll just a poll?

  1. R. Jenrette says:

    Re: Validity of polls. I don’t answer the phone unless I recognize the caller and it’s a call I want to take. I don’t answer on the chance it may be a pollster. So, I may be missing some polls or else the ones I could recognize are not calling or are not identifiable.
    I bet I’m not the only one doing this, So, how accurate can telephone polls be if a significant portion of the population don’t pick up the phone?
    And what about cell phones that are rarely identifiable?

Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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 )

Google+ photo

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

Connecting to %s

%d bloggers like this: