November 1, 201213 yr I should have broke out my old stats and logic textbooks before this election season, but I never expected it to end up this close.
November 1, 201213 yr Author Wasting time at work... Looking at some polling data in Wisconsin. Among "registered voters" Obama polls better. Among "likely voters" Romney polls better but is still left a point or so down. Undecideds still range in the 2-3% range (which I find unreal at this stage). The big question is who are those 2-3% of "likely voters" (that are STILL undecided) vote for. This thing may not end up being very close in the Electoral College but there are going to be some very, very close state races.
November 1, 201213 yr Wasting time at work... Looking at some polling data in Wisconsin. Among "registered voters" Obama polls better. Among "likely voters" Romney polls better but is still left a point or so down. Undecideds still range in the 2-3% range (which I find unreal at this stage). The big question is who are those 2-3% of "likely voters" (that are STILL undecided) vote for. This thing may not end up being very close in the Electoral College but there are going to be some very, very close state races. According to an article I posted in another thread last week, those who are undecided come election time tend to break towards the challenger (when there is an incumbent running) at a clip of around 80%.
November 1, 201213 yr But he is, because he equates things and gives weight to things, like which party is more likely to turnout, that he has no true clue on. If he uses the same %'s as 2008, then he's going to be way off IMO. I do not know how he has factored in the turnout or if he even uses that. However, you've hit upon the reason for the disparity in polls. R polls are using a bet that it will not be near the turnout as in 2008. D polls are using a similar number as 2008. That's the big question.
November 1, 201213 yr I do not know how he has factored in the turnout or if he even uses that. However, you've hit upon the reason for the disparity in polls. R polls are using a bet that it will not be near the turnout as in 2008. D polls are using a similar number as 2008. That's the big question. Not necessarily true on your second point....Pew and Gallup are not "R" polls and they've both been showing numbers that are not in line with the 08' turnout.
November 1, 201213 yr Article that discussed FiveThirtyEight plus why some of the polls used by the have to be factored in for bias (intentional as well as unintentional). Data, uncertainty, and specialization: What journalism can learn from FiveThirtyEight’s election coverage » Nieman Journalism Lab
November 1, 201213 yr Not necessarily true on your second point....Pew and Gallup are not "R" polls and they've both been showing numbers that are not in line with the 08' turnout. I was talking more about internal polling. See the link I posted before this about one of the potential issues with Gallup.
November 1, 201213 yr I do not know how he has factored in the turnout or if he even uses that. However, you've hit upon the reason for the disparity in polls. R polls are using a bet that it will not be near the turnout as in 2008. D polls are using a similar number as 2008. That's the big question. Not necessarily true on your second point....Pew and Gallup are not "R" polls and they've both been showing numbers that are not in line with the 08' turnout. "Do you plan on voting? [if yes] Who do plan to vote for?" = likely voter polls = expected turnout distribution.
November 1, 201213 yr Also, here's some perspective on statistical probability from Silver: "Mr. Obama is not a sure thing, by any means. It is a close race. His chances of holding onto his Electoral College lead and converting it into another term are equivalent to the chances of an N.F.L. team winning when it leads by a field goal with three minutes left to play in the fourth quarter. There are plenty of things that could go wrong, and sometimes they will. But it turns out that an N.F.L. team that leads by a field goal with three minutes left to go winds up winning the game 79 percent of the time. Those were Mr. Obama’s chances in the FiveThirtyEight forecast as of Wednesday: 79 percent."
November 1, 201213 yr Also, here's some perspective on statistical probability from Silver: "Mr. Obama is not a sure thing, by any means. It is a close race. His chances of holding onto his Electoral College lead and converting it into another term are equivalent to the chances of an N.F.L. team winning when it leads by a field goal with three minutes left to play in the fourth quarter. There are plenty of things that could go wrong, and sometimes they will. But it turns out that an N.F.L. team that leads by a field goal with three minutes left to go winds up winning the game 79 percent of the time. Those were Mr. Obama’s chances in the FiveThirtyEight forecast as of Wednesday: 79 percent." Correct. He is not saying Obama is getting 79% of the vote. He's saying there's a 79% chance he wins - could be by 10M, 1M , or 1.
November 1, 201213 yr This silly squabble speaks to pundits simply not understanding what is being presented.
November 1, 201213 yr Wasting time at work... Looking at some polling data in Wisconsin. Among "registered voters" Obama polls better. Among "likely voters" Romney polls better but is still left a point or so down. Undecideds still range in the 2-3% range (which I find unreal at this stage). The big question is who are those 2-3% of "likely voters" (that are STILL undecided) vote for. This thing may not end up being very close in the Electoral College but there are going to be some very, very close state races. And if the number is truly only 2-3%; it will take a big majority of those undecided voters actually voting en masse one way or another to make a difference. Remember - these folks are undecided. My "shot in the dark guess" is that the truly undecideds of the world will break no more than 55% - 45% one way or the other when they actually pull the levers. And 10% (the difference) of 2% to 3% of voters is 0.2% to 0.3% of the total.
November 1, 201213 yr Correct. He is not saying Obama is getting 79% of the vote. He's saying there's a 79% chance he wins - could be by 10M, 1M , or 1. Or by 100 electoral votes, 10 or 1?
Archived
This topic is now archived and is closed to further replies.