On May 6, expectations were high for Hillary Clinton. After all, the latest polls suggested the former First Lady had built up a 5-point cushion in Indiana and slashed Barack Obama's 20-point lead in North Carolina to 8. But over at FiveThirty Eight.com, an anonymous blogger (nom d'écran: "Poblano") wasn't convinced.
...the mysterious upstart projected that Clinton would win Indiana by 2 percent and lose North Carolina by 17—a far-less favorable outcome. When the results finally rolled in—1 in Indiana, 15 in North Carolina—Poblano had outperformed every established pollster. Clinton never recovered, but with the National Journal, the Guardian and the New York Post suddenly dissecting or demanding the secrets of his success...
Nate Silver the mysterious upstart and baseball stats prodigy, maintains
www.fivethirtyeight.com, which is definitely worth a look. What makes his site different? From his FAQ page:
Firstly, we assign each poll a weighting based on that pollster's historical track record, the poll's sample size, and the recentness of the poll. More reliable polls are weighted more heavily in our averages.
Secondly, we include a regression estimate based on the demographics in each state among our 'polls', which helps to account for outlier polls and to keep the polling in its proper context.
Thirdly, we use an inferential process to compute a rolling trendline that allows us to adjust results in states that have not been polled recently and make them ‘current’.
Fourthly, we simulate the election 10,000 times for each site update in order to provide a probabilistic assessment of electoral outcomes based on a historical analysis of polling data since 1952. The simulation further accounts for the fact that similar states are likely to move together, e.g. future polling movement in states like Michigan and Ohio, or North and South Carolina, is likely to be in the same direction.
Other notable alternatives to 538 for keeping track of the running election include Pollster.com and
Electoral-vote.com.
No comments:
Post a Comment