Political Animal

Blog

August 21, 2012 4:45 PM Can You Say “Outlier?”

By Ed Kilgore

It is apparently important for the psychology of conservatives right now to convince themselves and everyone else that Paul Ryan’s selection as Veep has created a surge in the GOP’s direction. Never mind that we are in a silly season of polling where “bounces,” if they exist, will almost certainly subside. The Cause must be moving steadily towards victory!

This occurred to me when noting on an aggregator site that I use this item from a Fox News affiliate in Detroit:

Foster McCollum White Baydoun (FMW)B, a national public opinion polling and voter analytics consulting firm based in Michigan and representing the combined resources of Foster McCollum White & Associates (Troy, Michigan) and Baydoun Consulting (Dearborn, Michigan) conducted a telephone-automated polling random survey of Michigan registered and most likely November 2012 general election voters to determine their voting preferences.
In what will be a significant blow to Democratic campaign efforts, native son Mitt Romney has climbed into the lead in Michigan’s Presidential contest. The naming of Wisconsin Congressman Paul Ryan has delivered a targeted affect on the Michigan and Midwest campaign dynamics.

Now it just so happens that I had a few minutes earlier read a post from Nate Silver that discussed a particularly crazy poll out of Florida:

I very much doubt that Mr. Romney and Mr. Ryan will win Florida by 15 percentage points, as the Foster McCollum White Baydoun poll currently says. The survey is a huge outlier relative to the consensus of polls in Florida, which have been a bit variable but have pointed toward a race that is roughly tied….
The poll was weighted to a demographic estimate that predicts that just 2 percent of Florida voters will be 30 or younger. It’s a decent bet that turnout will be down some among younger voters this year, but that isn’t a realistic estimate. In 2008, according to exit polls, 15 percent of voters in Florida were between 18 and 30.
The poll also assumed that 10 percent of voters will be between the ages of 31 and 50. In 2008, the actual percentage was 36 percent, according to the exit survey.
The poll projected Latinos to be 7 percent of the turnout in Florida, against 14 percent in 2008. And it has African-American turnout at 10 percent, down from 13 percent.
If the turnout numbers look something like that in November, then Mr. Obama will lose Florida badly. He’ll also lose almost every other state; his electoral map might look a lot like Walter Mondale’s.

Nate went on to say that he was assigning the firm a “house effect” (i.e., a structural bias, perhaps unintentional) of 11 points in favor of the GOP, based on the Florida poll and an earlier poll of Michigan.

But you wouldn’t know any of this if you just happened to tune in to your local Fox News outlet and heard about this shocking new poll. Which is all the more reason to approach individual surveys—whether you like what you hear or don’t—with great caution.

Ed Kilgore is a contributing writer to the Washington Monthly. He is managing editor for The Democratic Strategist and a senior fellow at the Progressive Policy Institute. Find him on Twitter: @ed_kilgore.

Comments

  • lkt on August 21, 2012 5:00 PM:

    Is the McCollum at this firm the former AG of Florida, Bill McCollum?

  • c u n d gulag on August 21, 2012 5:05 PM:

    And it's not just WHO was polled, it was the questions that were asked, too.

    Both can skew a poll's results in one direction or another.

    I frankly am not looking at polls until about a week after Labor Day, when everyone settles in after vacations and whatnot, and starts to focus on the election.

  • c u n d gulag on August 21, 2012 5:07 PM:

    Oh, and if it's a phone poll, land, cell, or a mix?

    Land skews older and more Conservative.
    Cell skews younger and more Liberal.

  • Steve M. on August 21, 2012 9:52 PM:

    These guys have Hoekstra over Stabenow by 2 in Michigan:

    http://www.myfoxdetroit.com/story/19331141/fox-2-poll-hoekstra-has-lead-over-stabenow-in-michigans-us-senate-race

    Every other non-Rasmussen pollster who's polled the race this summer has Stabenow up by double digits:

    http://www.realclearpolitics.com/epolls/2012/senate/mi/michigan_senate_hoekstra_vs_stabenow-1817.html#polls

    Pathetic.

  • biggerbox on August 22, 2012 11:07 AM:

    Has anyone factored in the effects of voter suppression, er "voter I.D." laws on turnout in these polls? I can't help but notice all the groups under-represented in that poll are ones targeted by the GOP anti-vote effort.

  • raindog on August 23, 2012 10:08 AM:

    My favorite "question" from those polls:

    Wisconsin Congressman Paul Ryan has been selected as the Republican vice presidential
    nominee. Congressman Ryan has proposed federal budgets that drastically cut the federal deficit,
    cuts taxes on job creators and proposes the reform of Medicare and Social Security benefits. The
    Tea Party and business groups support Ryan’s budget as fiscally responsible, reducing the size
    and cost of unsustainable programs. Democrats, senior citizens groups and a number of
    economists oppose Ryan’s budget proposal citing it gives the richest Americans a tax cut,
    privatizes Social Security and Medicare and will have a negative effect on the economy. Do you
    support Congressman Ryan’s budget plan for the federal government?

  • Eric Foster on August 28, 2012 11:57 PM:

    Hello.
    My name is Eric Foster, President of Foster McCollum White & Associates. I am the lead pollster for our firm and our partnership with Baydoun Consulting and Douglas Fulmer & Associates and I wanted to address a couple of items that created some confusion in our polling release.

    Our polling call list was weighted to the historical weights for age, gender, race, region and congressional district area. Our list is also comprised of voters with previous voting histories in Presidential, state and local elections. We include the moderate and low performance voters, but the call files do contain a significant portion of voters who have a likely history to participate. Our PVBA model reviews election statistics for age, gender, voting participation pattern, gender and socio-economic factors to determine the likely voting universe for an upcoming election. Our turnout models are based on state based historical turnout statistics provided by the municipal and county clerks and secretaries of state’s office of a state for age, gender, party, ethnicity and voting method (early, absentee, poll location) instead of exit polls.

    The reason why it is difficult to contact people via cell phones is The Telephone Consumer Protection Act (TCPA) (47 U.S.C. 227 , 47 CFR 64.1200) prohibits the use of an “automatic telephone dialing system” to contact “any telephone number assigned to a …cellular telephone service” without “express prior consent” from the party being called. Based upon this federal law, we call landlines

    Our PVBA model reviews election statistics for age, gender, voting participation pattern, gender and socio-economic factors to determine the likely voting universe for an upcoming election. Our turnout models are based on state based historical turnout statistics provided by the municipal and county clerks and secretaries of state’s office of a state for age, gender, party, ethnicity and voting method (early, absentee, poll location) instead of exit polls. We trust the reliability of the election statistics from the clerks’ offices to give us value data reads on future elections. For example, Michigan has a historical Presidential participation variance of 18.4% from the baseline voter model and has an -18.08% historical gubernatorial participation variance. The swing is equal to 2.3 million moderate and low performance voters in Michigan for every given Presidential election who primarily leave the participation rolls for the gubernatorial election. The difference between a Governor Snyder and Governor Bernero was the complete absence of the low performance voters and a 15% participation rate among moderate participation voters. If Bernero gets the participation rate of Granholm’s re-election in 2006 (85% moderate performing voters and 25% low participation voters) He defeats Snyder by 200,000 votes and wins 40 counties. This model allows us to help our political clients understand their election audience more clearly than exit polling. We then use it in assessing our polling models to help us gauge data quality and participation models.

    When we call through the list, we report the demographics of the respondents without weight. If our demographics match the likely voter demographics for the polling study. If there are underrepresented groups within our aggregate respondent universe, we use our weighting model to adjust for their representative weight and the groups reflected polling preference for the baseline questions. We still will report the un-weighted demographics of our respondents because they reflect the prevailing interest level of the voting groups at the time of our polling survey.

    Based on the respondent universes, we made the adjustment weight for the five underrepresented groups in Florida based on our PVBA model. We analyzed the respondent’s participation rates to our data models for Florida and also considered the recent spike in Presidential election