Archive for November, 2012

Election 2012 – Pooling Polls Works

Icon Written by Jeff on November 10, 2012 – 11:58 pm

Poll aggregators Simon Jackman, Drew Linzer, Nate Silver, and Sam Wang all made extremely accurate predictions for both the 2012 Electoral and popular vote outcomes. Why were they so good?  The most important reason is that they all developed statistical models based on state polls.  They also avoided subjectivity by using consistent statistical criteria for […]

Election 2012 Final Prediction

Icon Written by Jeff on November 5, 2012 – 11:32 pm

My final predictions are that Barack Obama will receive 332 electoral votes and Mitt Romney will receive 206.  This is the same as the Princeton Election Consortium arrived at under different assumptions but using only state polls. The current results for all states are in State Polls 11-5-12.  Florida (Figure 1) remains a tossup, but […]

Election 2012 – 11/3

Icon Written by Jeff on November 3, 2012 – 11:38 pm

Colorado (Figure 1) has shifted to undecided since my last post based on an alpha = 0.01 criterion for deciding that a percentage difference between Obama and Romney is significant.  The current results for all states are in Table 1. The predicted national vote difference stands at 3.0%. State Polls 11-3-12 As of today, the […]

Election 2012 – 11/2

Icon Written by Jeff on November 3, 2012 – 12:14 am

Little has changed since my last post.  Since I began pooling polls of the states about two weeks ago, I have added about 250,000 likely voters and little has changed.  I suspect that fluctuations in enthusiasm have settled down since the third presidential debate resulting in little change. At the alpha = 0.01 level of […]