London, April 2 : Researchers have come up with an accurate way of predicting Oscar winners.
Iain Pardoe of the University of Oregon in Eugene and Dean Simonton of the University of California, Davis, adopted a statistical approach to analyse the histories of around 1600 Oscar nominees between 1928 and 2006 in the four major categories, namely best picture, director, leading actor, and leading actress.
Based on their analyses, the researchers chalked out several factors correlating with Oscar wins, including previous nominations and Golden Globe wins.
They then plugged the factors thus identified into a statistical model, and "predicted" the winners from their track records.
The researchers said that the accuracy of their model for the 30 years leading up to 2006 was at least 70 per cent for all four categories, reaching 93 per cent for best director.
"It is quite a dramatic improvement on just pure random guesses," New Scientist magazine quoted Pardoe as saying.
The statistical model, described in the Journal of the Royal Statistical Society, scored three out of four in Los Angeles last month, predicting that Daniel Day-Lewis would win best leading actor, and the Coen brothers would scoop best director and picture for their film No Country for Old Men.