University of Colorado Model Still Predicts A Romney Win On Election Night

October 8, 2012 10:38 am

by Nathan · 14 comments

The University of Colorado’s quadrennial model to predict who will win the electoral college vote allocation has been updated with the most recent economic data.  It still predicts a win for Mitt Romney on November 6th:

According to their updated analysis, Romney is projected to receive 330 of the total 538 Electoral College votes. President Barack Obama is expected to receive 208 votes — down five votes from their initial prediction — and short of the 270 needed to win.

The new forecast by political science professors Kenneth Bickers of CU-Boulder and Michael Berry of CU Denver is based on more recent economic data than their original Aug. 22 prediction. The model itself did not change.

“We continue to show that the economic conditions favor Romney even though many polls show the president in the lead,” Bickers said. “Other published models point to the same result, but they looked at the national popular vote, while we stress state-level economic data.”

While many election forecast models are based on the popular vote, the model developed by Bickers and Berry is based on the Electoral College and is the only one of its type to include more than one state-level measure of economic conditions. They included economic data from all 50 states and the District of Columbia.

Of course, it’s only a model, but it’s been a fairly accurate model:

The state-by-state economic data used in their model have been available since 1980. When these data were applied retroactively to each election year, the model correctly classifies all presidential election winners, including the two years when independent candidates ran strongly: 1980 and 1992. It also correctly estimates the outcome in 2000, when Al Gore won the popular vote but George W. Bush won the election through the Electoral College.

What’s interesting is to see how the battleground states are predicted to go by this model:

Of the 13 battleground states identified in the model, the only one to change in the update was New Mexico — now seen as a narrow victory for Romney. The model foresees Romney carrying New Mexico, North Carolina, Virginia, Iowa, New Hampshire, Colorado, Wisconsin, Minnesota, Pennsylvania, Ohio and Florida. Obama is predicted to win Michigan and Nevada.

In Colorado, which Obama won in 2008, the model predicts that Romney will receive 53.3 percent of the vote to Obama’s 46.7 percent, with only the two major parties considered.

So, there you have it.  Interpret the numbers as you will.  As usual, your mileage may vary.  How do you predict the electoral college will be divided on November 6th?

saltycracker October 8, 2012 at 11:10 am

When you pump a trillion or so into the system it feels good & the market rises.
It also felt great when someone loaned us so much money and we built houses.

Scott65 October 8, 2012 at 11:11 am

I think you are reaching with this one…I’ve not seen a credible estimate, even post debate that give Romney an edge in the EC. 538 still gives Obama an 80+% of winning the EC

Scott65 October 8, 2012 at 11:15 am

I think you should read this…it puts this prediction model in the same context as how many times the redskins win as a predictor of the election…
http://abcnews.go.com/Politics/OTUS/wacky-ways-predict-presidential-election/story?id=17293644#

Scott65 October 8, 2012 at 11:17 am
Nathan October 8, 2012 at 11:29 am

Well, 8 out of 8 is a good record. It could be wrong, but it could be right. We’ll see on election night.

Scott65 October 8, 2012 at 11:38 am

yeah, if they update the model the day before the election…lol

Chris Huttman October 8, 2012 at 12:33 pm

8 out of 8 would be a good record – but they are simply applying past data to explain past results. Big difference. I can run a model that predicts based on some esoteric variables what stocks in the Dow Jones Industrial Average will go up and down over the last 8 days. It will be a perfect model – since I’m driving through the rear view mirror. And it will be worthless model for day 9.

Among other things – this model automatically gives the Republican a better chance of winning if economic conditions improve. Umm….

ramblinwreck12 October 8, 2012 at 1:09 pm

If you’re looking for an election model that’s tried and true, you should check out the one developed by Alan Abramowitz over at Emory. It’s considered one of the best in the country:

“The model’s average error in elections after World War II is only 1.1 percent, and the correlation between the model’s results and the actual election results is an amazing 97 percent.”

This year he’s got Obama winning the popular vote by 1.2%, just above the margin of error.

Jackster October 8, 2012 at 11:24 am

To quote Monty python,”Camelot! Camelot! it’s only a model”

Romney will get my vote if he articulates a plan which includes universal coverage

Obama will get my vote if he brokers a deal with the afghans and Iraqis that bring out troops home NIW.

Harry October 8, 2012 at 11:57 am

From the Business Insider: “Last time the economy supposedly added 873,000 jobs it was growing at a white-hot 9.3%. Growing at 1.5% today.”

Doug Deal October 8, 2012 at 1:04 pm

I do not know why people give Nate Silver special attention with his predicitions. He completely blew the UK elections and pretty much every foreign election he has “predicted”. I was closer to the House numbers last year and I pulled the number out of a place the sun doesn’t shine. Like Zogby, he was close once and eventually people will see him in the same light when a new golden boy gets selected.

Buzz Brockway October 9, 2012 at 8:55 am

If he keeps predicting stuff he’ll eventually be right, or not. After the election we’ll see another round of articles about which pollster is “hot” and how the news business relies too heavily on polling in their reporting.

Doug Deal October 9, 2012 at 11:25 am

True Buzz. God forbid we make news out of something other than randomly sampled opinions.

The Last Democrat in Georgia October 8, 2012 at 2:08 pm

“In Colorado, which Obama won in 2008, the model predicts that Romney will receive 53.3 percent of the vote to Obama’s 46.7 percent, with only the two major parties considered.”

Oh, the irony! Could it be that Romney’s so-called “47 percent” comments were forecasting the outcome of the election?

Romney 53%, Obama 47%.

Comments on this entry are closed.