Poblano has conducted an interesting analysis of the New Hampshire vote in 2004 and 2008, using a multiple regression analysis on a town by town basis. The purpose of the analysis is to estimate who 2008 supporters of Clinton, Obama and Edwards backed in 2004. Since the study is based at the town level, rather than the more precise individual voter level, it should be taken with a grain of salt. Still, it is a compelling insight into the different coalitions within the Democratic Party:
This regression produces a number of coefficients that represent how much support was transferred from one candidate to another. For example, if the coefficient between John Kerry and Hillary Clinton is .73, that means that for every percentage point that Kerry had in a district in 2004, Hillary tended to pick up .73 percentage points in 2008. (…)
Clinton
.73 Kerry
.66 Lieberman
.18 Clark
.12 Edwards '04
-.05 Dean
Obama
.93 Dean
.45 Clark
.38 Edwards '04
.15 Lieberman
.09 Kerry
Edwards (2008)
.37 Edwards '04
.37 Clark
.24 Kerry
.15 Lieberman
.00 Dean
As Matt noted yesterday, the campaign seems to be coming down to identity politics. Activists and campaigns seem ready to play full hands of age, race and gender cards. With Obama relying primarily on non-Kerry supporters in New Hampshire, in order to win the nomination nationwide he will need both the overwhelming backing of African-Americans and a large influx of new primary voters. Otherwise, Clinton's domination of the Kerry vote will simply be too much. In 2004, Nevada was one of Kerry's best states, as he secured 64% in the February 14th caucuses. If Clinton's campaign really is the Kerry and Lieberman coalitions reborn, while Obama and Edwards are splitting the remainder, then Clinton probably wins out. Older women are the largest identity group in the Democratic primary electorate. It will take both a nearly unified, and greatly expanded, progressive creative class plus African-American coalition to have any chance against her.