Monday, September 27, 2010

KY-Senate: Don't Believe Every Poll You See

Here is an important piece of advice for those who are monitoring the 2010 election polling data on a daily basis.  Look at how the pollster breaks down the party identification.  The Survey USA poll of the Kentucky Senate race that was released this weekend should serve as a classic example of how erroneous party ID weightings can distort a survey.  After showing Rand Paul with a 15 point lead over leftist Jack Conway just three weeks ago, Survey USA now has Conway within two.  But here is the kicker.  The poll taken earlier this month had a party ID breakdown of 47 D 10 I 42 R.  That is actually slightly less favorable to the GOP than the disastrous 2008 turnout of 47 D 15 I 38 R (in which McCain still won).  Remember that there is no doubt that there will be more Republicans turning out to vote in Kentucky this year.  The only question is how much more?  However, nobody disputes that the turnout figures will be much more favorable than those of the past two elections cycles.

This brings me to the most recent Survey USA poll that shows Paul leading Conway by a paltry 49-47 margin.  The party ID weightings of the survey were as follows:  51 D 12 I 38 R!  Does anyone really believe that a majority of the voter turnout in a staunch conservative state, in a staunch conservative year, in a state where Obama's approval ratings are in the toilet, will be Democrats?  Is it really possible for voter turnout models in 2010 to be worse for the GOP than 2008?  I have no proof that Jack Conway is not on the rise, however if he is, it will not be as a result of an impossible voter turnout model.

Public Policy Polling (PPP) is a good case study of what a difference party ID weightings have on the survey results.  Towards the beginning of the cycle, they had polls that showed Senator Burr in North Carolina in a dead heat with his opponent.  This is because they had similar turnout models to the abovementioned Survey USA poll.  Now that they weight their surveys to reflect a more realistic turnout model for 2010, most of their polls are spelling doom for the Democrats.  The devil is always in the details.

1 comment:

Bob said...

Very excellent point--and one that is ignored 99% of the time by the liberal media.