Milwaukee J-S Poll

Byline: | Category: Uncategorized | Posted at: Wednesday, 31 October 2012

The Milwaukee Journal-Sentinel has a poll of Wisconsin out this afternoon.  The top line has the race going from an Obama 1-point lead two weeks ago to an 8-point lead today.  That’s a shift that defies common sense. 

However, that doesn’t mean that they did the poll wrong.  Let me explain.

A poll of about a 1,200 respondents in its sample will have a margin of error of about 3% at the 90% confidence interval.  If the actual race is Obama 45 – Romney 45, and you select a hundred different random samples from the population, you would expect that 90% of those samples to give you a result of somewhere between Romney 42 and Romney 48.  The other ten polls will be outliers of more than the margin of error of 3 percentage points.

I don’t see anything necessarily wrong in the demographices of sample polled.  Nor did I observe anything done differently from the poll the J-S did two weeks ago.  However, with little reason to believe that the race moved 8-points in Barack Obama’s direction, it is likely that either the earlier poll or this one is an outlier.  Given where everyone else is showing the state of the race in Wisconsin, it is probably this most recent poll that is the outlier. 

But my standard state poll caution applies:  Be very wary of media and university polls of states that are not routinely performed time and time again.  Polling at the state level can be very screwy and there are a lot of one-off polls performed with shady methodologies.

Finally, there is one odd thing about this poll.  It shows a 100% likelihood of voting even as there are 51 respondents who report being unregistered.  Now I believe that Wisconsin has same-day registration, so that might explain the unregistered but likely respondents.  However, that wouldn’t explain the other issue.  See the table below:

marquette_poll.jpg

Either the J-S includes only those who say that they are absolutely certain to vote plus those who report that they have early voted in their likely voter sample, or some segment of this likely voter sample is lying about their intent to vote.  Anyone know?

Share this post:

One Response to “Milwaukee J-S Poll”

  1. Lorenz Gude Says:

    Hmmm another last minute pro Obama outlier with some dubious methodology. Thanks for taking the trouble to do these mico analyses. They provide considerable insight into how polls MAY be a greater part of the media manipulation scenario than we realize. Consider this – when I taught Media Studies at university level (No not the postmodern kind, more McLuhan based) I always put a lot of emphasis on the ideal that TV news was predominantly drama – the pictures carry the main message and are cut for emotional effect. The words are then fit to the manipulated visual story which passes our truth filters because we accept the visual dramatic experience as real experience. The emphasis on the emotions is the difference between drama and reporting – fiction and non fiction. So what does a sudden shift in the polls cause to the emotions of the audience? Well, look what the first debate did to the emotions of the Non Fox Media! I voted about two weeks ago so there there is nothing more I can do but ride this emotional POLLER coaster and remember that it will be the voters, not the polls, which determine the result.