CU Election Forecast Model Predicts Romney Victory

August 24, 2012

Romney during a visit to Colorado earlier this year

DENVER–There was good news from Colorado this week for Mitt Romney: A University of Colorado prediction model that has correctly forecast the winner of the last eight presidential races points to Romney as the winner in 2012.

Ken Bickers, professor of political science at the University of Colorado Boulder, and Michael Berry, political-science professor at the University of Colorado Denver, announced this week that their state-by-state analysis shows the Republican capturing a majority of electoral votes.

“Based on our forecasting model, it becomes clear that the president is in electoral trouble,” said Bickers, who also serves as director of the CU in DC Internship Program.

The results show President Obama winning 218 votes in the Electoral College, well short of the 270 required for victory. Romney takes the remaining 320 electoral votes under the analysis.

While the study focuses on the electoral vote, the professors also predict that Romney will win 52.9% of the popular vote to Obama’s 47.1% when considering only the two major political parties.

Romney is also forecast to win Colorado’s nine electoral votes, although by a smaller margin than his national percentage. The model has him taking 51.9% of the popular vote, with Obama capturing 48.1%, when only the two candidates are considered. Obama won Colorado in 2008 by a margin of 54% to 45%.

The analysis did not include other presidential candidates like the Libertarian Party’s Gary Johnson and Green Party’s Jill Stein, but that hasn’t hurt its accuracy in the past. The model predicted the correct result in 1992, when Reform Party candidate Ross Perot ran strongly, and also in 2000, when Democrat Al Gore won the popular vote but Republican George W. Bush took the electoral vote.

The analysis factors in a host of economic data, including state and national unemployment figures and changes in real per capita income. Incumbency is also considered, although the model shows that a Democratic incumbent’s advantage evaporates when unemployment hits 5.6%.

“What is striking about our state-level economic indicator forecast is the expectation that Obama will lose almost all of the states currently considered as swing states, including North Carolina, Virginia, New Hampshire, Colorado, Wisconsin, Minnesota, Pennsylvania, Ohio and Florida,” Bickers said.

What distinguishes the Bickers-Berry model from other election prognostications is that it runs entirely on economic data, instead of subjective factors like the candidates’ approval ratings, vice-presidential picks and ad campaigns.

For example, the professors found that there was no statistical advantage conferred by the following: the location of the party’s national convention, the home state of the vice-presidential candidate, or the party affiliation of state governors.

The results“suggest that presidential elections are about big things and the stewardship of the national economy,” Bickers said. “It’s not about gaffes, political commercials or day-to-day campaign tactics. I find that heartening for our democracy.”

The news wasn’t all bad for Obama. Given that the data was collected five months before the Nov. 6 election, the professors say they plan to update their forecast in September. They also note that 50-50 states have been known to swing in unexpected directions.

“As scholars and pundits well know, each election has unique elements that could lead one or more states to behave in ways in a particular election that the model is unable to correctly predict,”  Berry said.

Comments made by visitors are not representative of The Colorado Observer staff.


Your email address will not be published. Required fields are marked *

The Complete Colorado
Colorado Peak Politics - Sometimes Unruly. Always Conservative.

Visitor Poll

Should illegal immigrant kids flooding the border be housed in Colorado?

View Results

Loading ... Loading ...

The Colorado Observer