March 16, 2008
The Pulitzer Prize for 2008 will be announced on April 7, 2008. So, who will win? A research scientist and Modern Firsts/Pulitzer Prize Award Books collector has conducted a regression analysis aimed at building a model that best predicts, to the extent that it can be predicted, the Pulitzer Prize award winning book for a given year. Regression analysis is a statistical method to determine what independent or predictor variables best predict a particular dependent variable. In this case, the dependent variable - that is, the variable being predicted - is winning the Pulitzer Prize for Fiction. This analysis incorporated over 30 independent or predictor variables such as newspaper notable and best book lists; other awards and award nominations for 2007; and authors previously nominated for the Pulitzer and other awards.
What follows are the 10 books that, according to this regression model, are most likely to win the Pulitzer Prize for 2008. Before listing those books, however, please keep in mind that this is in no way intended to suggest that one of the listed books will absolutely win the Pulitzer. There is still much that cannot be predicted about winning the Pulitzer Prize and lots of other factors that cannot be quantified as variables that certainly contribute to the award process. Readers should only consider this list for what it is intended to be, a fun exercise in second guessing (or pre-guessing) the Pulitzer Prize judges! Be forewarned, this model would certainly not have predicted the award to Jhumpa Lahiri for Interpreter of Maladies in 2000 or Richard Russo for Empire Falls in 2002. Also, because some authors are perennial award winners and nominees, their books are disproportionately likely to end up at the top in calculations such as this, so any book by Philip Roth or Joyce Carol Oates, for example, will likely wind up in the top 10.
Those caveats aside, the top 10 books written in 2007 that would be predicted to win by this model are (in order of probability):