Showing posts with label Nate Silver. Show all posts
Showing posts with label Nate Silver. Show all posts

Sunday, November 4, 2012

Amusing: Nate Silver starts back-peddling...

So, if Romney wins the national vote by +1% he has a 70% chance of winning? Of the last six polls, the average toter turnout model is Democrats +6 points. 2008 was Democrat +7 points.  Based on those skewed poll numbers the race is a tie. If Republicans turn out in larger numbers than 2008, and early voting indicates they are, Romney will win. If Republicans cut the Democrats voting edge in only half, Romney will win by about 3 points. It's time to throw in the towel Nate.


Saturday, August 4, 2012

Should the predictions of liberal's favorite election analyst Nate Silver scare Republicans?

The answer is no. Here is why. Nate Silver had a very good model in 2008. He can not be ignored in 2012, but Republicans and Romney supporters should not be overly concerned with Silver's predictions at this point.  Here is a screen capture of his current prediction as of 08/04/12.

This certainly look like a likely Obama victory. As did this capture from WayBackMachine on 08/07/08.

Nate Silver may have gotten the eventual winner correct, but his prediction in August of 2008 was off by almost 4% on the popular vote and a whopping 67 electoral votes. Here are the final 2008 results from CNN.

The truth is Nate Silver's models can only be as good as the polling numbers he has to work with and the mainstream polling is now all heavily skewed to a huge Democratic turnout. A PEW poll found +19 for Democrats. A recent CBS/NYT poll found a huge sample of expected Democratic voters in key swing states.
The CBS/NYT model has Democrats a +9 in Florida when in 2008 they were only a +3 and an even split in the 2010 midterms.  Ohio’s sample has exactly the split in 2008 (D+8), which is nine points better than Democrats did in the midterms.  Pennsylvania’s numbers (D+6) come closest to a rational predictive model, somewhere between 2008′s D+7 and 2010′s D+3, but still looking mighty optimistic for Democratic turnout.
If you think the Democratic turnout is going to be significantly larger than 2008, then, Romney is in trouble. If you believe, as I do, Republicans will match Democrats voter-for-voter or better in 2012, Romney has a good chance. As we get closer to the election, the pollsters will get more accurate because the final numbers are the ones they will be judged on. Nobody will remember these July and August polls. This allows Obama's mainstream media lapdog pollsters to arrange a little home cooking to help their favorite candidate look like a winner.

Saturday, October 9, 2010

Liberal Heartache: Nate Silver Predicts 50% Chance Republicans Will Gain 50 House seats


Republicans need 40 seats to tack back control of the House. It must really kill the liberals at the New York Times to admit Republicans will likely gain 50.
Our model now estimates that the Republicans have a 72 percent chance of taking over the House, up from 67 percent last week. Moreover, they have nearly even odds of a achieving a net gain of 50 seats; their average gain in a typical simulation run was between 47 and 48 seats. However, the playing field remains very broad and considerably larger are possible, as are considerably smaller ones.

Sunday, September 12, 2010

Election Analyst Nate Silver: Republicans have a 2 in 3 chance of claiming a majority of House seats in November


Democrats favorite election analyst, Nate Silver, is predicting Republicans have a 2 in 3 chance of claiming a majority of House seats this November.
Republicans have a two-in-three chance of claiming a majority of House seats in November, the FiveThirtyEight forecasting model estimates. And their gains could potentially rival or exceed those made in 1994, when they took a net of 54 seats from the Democrats.

Nate Silver also give the GOP a 1 in 5 shot ant taking control of the Senate. It's time to put Nancy Pelosi on suicide watch.

Wednesday, August 25, 2010

Nate Silver Predicts Democrats to Lose 6 or 7 Senate Seats


The latest FiveThirtyEight forecasting model has Democrats losing 66.5 seats in the Senate this fall.
On average, over the model’s 100,000 simulation runs, the Democrats are projected to lose a net of six and a half Senate seats, which would leave them with 52 or 53 senators.

The model also predicts there is a 20% chance of Democrats losing control of the Senate to Republicans.
The Democratic majority is in increasing jeopardy in the Senate, according to the latest FiveThirtyEight forecasting model. The Democrats now have an approximately 20 percent chance of losing 10 or more seats in the Senate...

Nate Silver is an American statistician whose work first appeared on Daily Kos. That should tell you his political affiliation. However, he has a good record of accuracy.