David Strömberg

WH 2008 Analysis, Oct. 29

Phone: +46 8 16 43 77
Fax: +46 8 16 14 43
E-mail: info@iies.su.se
Webmaster:
www@iies.su.se

Last updated,

 October 1, 2008

How the probabilities are estimated

Compared to the previous analysis on October 20. Obama's chances of winning remain about the same. A slightly fall in the polls is compensated by lower uncertainty as there are fewer days left to the elections.

 Obama has an 84 percent chance of winning the elections, receiving an average vote-share of 52 percent of the two-party vote share and an average 319 electoral votes. The risk that the president elect will not receive a majority of the popular votes is around 8 percent. It is more likely that Obama will be in this position (5 percent) than McCain (3 percent). Consequently, Obama benefits slightly from having the Electoral College system (this increases his chances of winning by 2 percent).  

The Bradley effect

I have estimated the Bradley effect based on 421 elections for House, Senator and Governor, 1998-2006, containing 26 black candidates. The effect is 2-3 percent of the two-party vote share. If there will be a Bradley effect of the same size as the average for the 22 House, Senate and Governor races 1998-2006 for which I have data. The statistics are the following.

The table below show the forecasted democratic vote shares (absent the Bradley effect), win percentages and the share of candidate visits that should go to each state, based on opinion polls available October 29.