You are using an outdated browser.
Please upgrade your browser
and improve your visit to our site.

A Peek At Surveyusa's Methodology

After the California primary, I mentioned that what set SurveyUSA apart from all the polls (and prognosticators) predicting a better Obama showing was that SurveyUSA had a great likely voter screen that foresaw the huge surge in Latino turnout. Mark Blumenthal over at has some information on how it works (click through for more details):

SurveyUSA's approach to likely voter modeling is comparable to that used by Iowa's Ann Selzer, in that they do not make arbitrary assumptions about the demographic composition of the likely electorate. As SurveyUSA's Jay Leve explains, they "weight the overall universe of Texas adults to U.S. census" demographic estimates, then they select "likely voters" based on screen questions and allow their demographics to "fall where they may." So some of the demographic variation from survey to survey is random, but large and statistically statistically significant variation should reflect real changes in the relative enthusiasm of voters.

But arbitrary assumptions are what make the process so much fun! Anyway, it's anybody's guess whether this method will work as well in Texas as it did in California, but it results in a 49–45 Obama lead, thanks in large part to exceptionally high predicted black turnout and relatively lower Latino turnout (although, perhaps surprisingly, Obama does slightly better among Latinos than he does among whites).

--Josh Patashnik