Nov
02
2008
Another leading polling expert, this time for the Washington Post, comes clean about the uncertainties in the voter turnout models which have produced Obama leads of +2 (a tie) to +15 in the same week from different pollsters. A must read for Americans so they understand why polls usually get the race wrong (only 1 [...]
Nov
02
2008
If the early voting trends are a hint of what is to come on Tuesday then the news is not great for Obama. In Wisconsin (deep blue normally) early voting is up – across the board. It is up by 25% in democrat heavy big cities, and up 40-50% in GOP havens outside the cities: [...]
Nov
02
2008
Yesterday I noted PA was starting to drift rightward with a lot of polls showing Obama’s once commanding lead cut in half. In fact Obama lost another point in the Morning Call daily poll, now down to a 7% lead, even though Morning Call has held massive Party ID edges for the democrats (they don’t [...]
Nov
01
2008
The polls in PA running up to the final day are nothing short of stunning. The most leftward poll out there – the Morning Call which doesn’t do any party ID weighting in its samples – has seen Obama’s leads shaved severely from somewhere around 15% to 8% (no one is keeping a history of [...]
Nov
01
2008
We come to it at last. The final weekend, the final push, the final group of voters to decide. And the headline news is McCain finally pulling ahead in a national poll (if only for a day). “Is McCain making a move? The three-day average holds steady, but McCain outpolled Obama today, 48% to 47%. [...]
Oct
30
2008
The race is clearly tightening, according to another new national poll out today: As the candidates make their closing arguments before the election, the race has tightened with Barack Obama now leading John McCain by 47 percent to 44 percent among likely voters, according to a FOX News poll released Thursday. Last week Obama led [...]
Oct
30
2008
It seems those rumors of Obama being in trouble in PA might very well be true: Obama 47, McCain 43, Undecided 9 Dates conducted: Oct. 27-28. Error margin: 4 points. Given the margin of error this is a statistical tie.
Oct
30
2008
Update: For those interested in an expert opinion on early voting and polling drop by DJ Drummond today – end update If early voting in Florida is any indication what will happen across this country come next Tuesday (and there is little reason to assume it will be some crazy outlier well outside the norm) [...]
Oct
29
2008
Tonight I continue my monitoring of the two families of polls being produced this year by pollsters in order to provide our readers insight into how the presidential race is playing out based on two  different assumptions on turnout models. The tracking polls in the ‘traditional’ family use historic voting trends to weight things like [...]
Oct
29
2008
.. about early voting trends and exit polls can be found at the NY Times Caucus Blog.
Oct
29
2008
Early voting patterns are showing two things – lots of voters are coming out, and many more are ‘democrats’. Here is a list of stories that show that early voting trends are indicating record voter turnout – which cannot be solely due to Democrats in the end. But the message is clear – if you [...]
Oct
29
2008
If Obama loses PA he is in deep trouble. The public polls show an Obama blow out, but behind the scenes rumors persist: Tonight we spoke with a friend from Hillary Clinton’s campaign who is now working for McCain/Palin — and is specifically working with Democrats for McCain in Pennsylvania. We worked with her in [...]
Oct
29
2008
I know I am an unknown and anonymous blogger whose mathematical skills can easily be questioned, but it is just strange to see how slow some light bulbs are turning on in the news media. As I noted last night, the poll confusion is not confusing at all. Â There are two families of polls out [...]
Oct
28
2008
McCain has allowed some of the campaign’s internal poll information to come out to the public – probably to give hope and energy to his base and generate some news.  I am sure both objectives will be achieved. Here are the more interesting tidbits: The campaign is functionally tied across the battleground states … with [...]
Oct
28
2008
When NASA or the DoD need to track a satellite we use multiple parallel models to account for gravity, solar pressure, the height and drag of the atmosphere (what little there is at orbital altitudes) and a variety of other models. We update the measurements in all these factors and run statistical models, weighting newer [...]