Predicting the Future

The Strömberg Model
by Charlie Leck
Saturday morning: 5:00 AM

The phone rang at 4:15 this morning – a call from England. It was a startling way to wake up on a morning when we usually sleep until 4:30 or so. It's a Midtown Farmers Market morning for my wife and she heads out with the pickup truck and freezer unit at about 6:15. I shook the cob webs free and decided to catch up on a few of my favorite blogs. I'm behind on Freakonomics, one of my very favorite blogs, so I ran through the stuff I've missed out on there and came upon Justin Wolfers' June 13^th posting, Election '08: Markets and Models. If you're a political junkie, as I am, I highly recommend you take this one in.

I was surprised to learn that one of the most respected scholars examining American politics is a Swede, David Stromberg. He is an Associate Professor at the Institute for International Economic Studies at Stockholm University. Wolfers says:

"The Strömberg model is, in my view, the leading quantitative election-forecasting model — both parsimonious and sophisticated. By building up forecasts state-by-state based on a slew of economic and political factors (details here), his model can
not only predict who will win, but also the likelihood that each state will be pivotal. In turn, this makes David's approach ideal for campaigns trying to figure out where to direct campaign resources."

The Strömberg Model gives the Democrats a 65 percent chance of winning the presidential election this fall and indicates they'll take 51 percent of the popular vote and the Electoral College by a 294-244 margin. The odds I like, but the closeness of the popular vote makes me uneasy. It is worth heeding some of Strömberg's reasoning.

Strömberg sees the Democrats doing well in Ohio, Pennsylvania and Michigan and not so well in Florida. Strömberg feels it is too early to pay attention to opinion polls and that a few weeks after the conventions they'll make more sense.

"The Strömberg model also suggests that there is a one-in-four chance that the 2008 race will come down to the decisions of less than one-in-100 voters in just one state, a situation that would be similar to Florida in 2000, or Ohio in 2004."

It sounds like the following are key states that will get an extreme amount of attention from the campaigns:

• Ohio
• Pennsylvania
• Michigan
• Florida
• Colorado
• Virginia
• California

The full article by Strömberg and Wolfers appeared in the Wall Street Journal.

Here's what makes me exceedingly nervous about the Strömberg report on the upcoming election:

"The most important factor highlighted by our analysis is simply the substantial uncertainty about the likely outcome in November. It is this uncertainty that leads us to suggest a strong Democratic performance, while still allowing for a 36% chance of a Republican victory.

"Alternatively phrased: Sen. Obama's lead is real, but shaky."

It's a long time from June to November and too early to get excited about all this stuff. There are so many odd things that will happen to both candidates and we've got the Fox News and Rush Limbaugh factor with which to contend. Ugh!