Page 14 of 20 FirstFirst ... 1213141516 ... LastLast
Results 157 to 168 of 235
  1. #157
    Join Date
    Sep 2009
    Posts
    21,926
    Blog Entries
    1

    Re: RCP Electoral Map Thread

    Quote Originally Posted by Haloti92 View Post
    Both of them just analyze poll results. The concerns people have cannot be addressed by them because the concerns are about the data they are analyzing (and its accuracy) not their actual analyses. They both start with the assumption that the polls are showing them the actual electorate.

    The fact is, with early voting expansion, cell phones, Caller ID, an extra partisan electorate, and more polling being done by more pollsters with more methodologies, it is not a given that these polls can be relied on to the extent they are being relied on.

    That said, the extra poll numbers combined with averaging them should even out the anomalous, bad apples, but it wouldn't catch a systematic failure/asumption that exists throughout the majority of the polls. Obviously, whether there is a systematic failure is clearly up for debate, and the burden of proof is on those claiming there is, and as of yet I have not heard great evidence, though I have heard some compelling speculation. We won't know until Tuesday.
    Best breakdown I've read by far about the analysis of the polls.

    On Polling Models, Skewed & Unskewed





  2. #158

    Re: RCP Electoral Map Thread

    Quote Originally Posted by Haloti92 View Post
    Both of them just analyze poll results. The concerns people have cannot be addressed by them because the concerns are about the data they are analyzing (and its accuracy) not their actual analyses. They both start with the assumption that the polls are showing them the actual electorate.

    The fact is, with early voting expansion, cell phones, Caller ID, an extra partisan electorate, and more polling being done by more pollsters with more methodologies, it is not a given that these polls can be relied on to the extent they are being relied on.

    That said, the extra poll numbers combined with averaging them should even out the anomalous, bad apples, but it wouldn't catch a systematic failure/asumption that exists throughout the majority of the polls. Obviously, whether there is a systematic failure is clearly up for debate, and the burden of proof is on those claiming there is, and as of yet I have not heard great evidence, though I have heard some compelling speculation. We won't know until Tuesday.
    Again, this is why I said to visit their site and read their posts...they discuss these very points you bring up (see Nate's article on anti Romney poll bias). Again, both these guys have VERY accurate track records on elections and 2012 should be no different. It's one thing if partisan hacks like Michael Moore, Rachel Maddow, or Bill Maher are throwing these sort of #s around, but these guys make a reputation on being objective and accurate. If Obama was the one that was consistently 1-3 points behind Romney in Ohio polls, then the numbers would be swinging the other way Romney, that's how important that state is for both candidates...but believe what you wish. Nothings a sure thing so we'll see who is right on Tuesday.





  3. #159
    Join Date
    Apr 2009
    Posts
    13,453
    Blog Entries
    5

    Re: RCP Electoral Map Thread

    TEAM O IS WORRIED ABOUT PENN. FROM FREEPERS:


    I didn't think PA was really a possibility until last couple days. Polls are looking good. However some real clues lie in the size of the crowd Romney pulled in a district Obama won with 53% in 2008. Additionally Clinton going there for 4 stops tomorrow. That is important for two poins. Dems worried. And the bigger point (my editorial belief) they know Obama isn't popular but PA liked Clinton, so they are sending him to try to pull the indy's and Dem's they are losing! The momentum is there PA people just get out and vote





  4. #160

    Re: RCP Electoral Map Thread

    Quote Originally Posted by kojo View Post
    Again, this is why I said to visit their site and read their posts...they discuss these very points you bring up (see Nate's article on anti Romney poll bias). Again, both these guys have VERY accurate track records on elections and 2012 should be no different. It's one thing if partisan hacks like Michael Moore, Rachel Maddow, or Bill Maher are throwing these sort of #s around, but these guys make a reputation on being objective and accurate. If Obama was the one that was consistently 1-3 points behind Romney in Ohio polls, then the numbers would be swinging the other way Romney, that's how important that state is for both candidates...but believe what you wish. Nothings a sure thing so we'll see who is right on Tuesday.
    I have read what they say, but it doesn't answer the questions. It amounts to: we have no reason to think these polls are any less accurate than 4 years ago (or 8 years ago, etc). But that is exactly the issue. If something is special about this election, and one could argue that these elections are so rare as to make every one special in some way, then the polls may be missing something (as it relates to the electorate vs who they are sampling) which would, in turn, make Silver's and Wang's conclusions erroneous. Their conclusions wouldn't be erroneous due to their math, but merely the data sets they were using (being given by pollsters).

    Your constant mention of their VERY accurate track records, besides being somewhat meaningless in the sense that you are only talking about 2 elections (one of which was a blowout that many people predicted, and which Silver was fed more accurate internal polls from the Obama campaign) which is a nearly non-existent sample size, is also a textbook fallacy.

    Yes, if Romney were ahead in the polls by the same numbers Obama is then, yes, Wang and Silver would have mirror image predications (most likely, Silver does have some subjectivity in his methodology that might be affected by his bias, but if so, is fairly slight). This is exactly what I am saying. They are analyzing the polls. The issue is not with their math, it is with the polls they are using. That is if an issue exists at all, and it might not.

    It has nothing to do with what to "believe," it has to do with what is true.

    It is an absolute fact that these polls could be making universal assumptions that are incorrect that lead them to produce biased results. For example they all weight by demographics, and choosing to assume the electorate will be 74% white vs 76% white is enough to move their poll results 2 points. Same goes with assumptions about women vs men, Hispanics, blacks, ages 18-29, ages 65+, etc etc. Every poll weights their results to fit an assumed electorate. Normally these electorates change slowly and in semi-predictable ways, but because the change between 2004 and 2008 was so huge, it is a legitimate question as to whether the trend (of change) continues, whether the electorate remains the same (as 2008), or even possibly goes back to something between 2004 and 2008 (because Obama hype is less and the groups that turned out in 2008 in proportions larger than usual will actually turn out less this time). There is also the very real issue about early voting affecting the likely voting screens, which has been mentioned on this thread. The point is, the polls are by no means factual; they are a mix of science and art, and this year the art may make up a larger portion than normal due to very rare election circumstances.

    We will indeed find out Tuesday. And frankly I tend to believe that the polls will likely be somewhat accurate. I do think Romney will win Virginia (contrary to Silver's prediction) and Florida. But as for Ohio or another, I wouldn't bet a lot on it, myself. Maybe Colorado or New Hampshire, which won't matter without Ohio. I think Pennsylvania is very unlikely and states like Michigan/Minnesota, lol, have 0% chance (literally 0%).
    Last edited by Haloti92; 11-05-2012 at 01:43 PM.





  5. #161

    Re: RCP Electoral Map Thread

    http://fivethirtyeight.blogs.nytimes...ically-biased/

    Fallacy? Well do YOU believe there is something different about this election or not (the vast polls all being fundamentally off)?What exactly did he say in that article here that doesn't jive with you?





  6. #162

    Re: RCP Electoral Map Thread

    Quote Originally Posted by kojo View Post
    http://fivethirtyeight.blogs.nytimes...ically-biased/

    Fallacy? Well do YOU believe there is something different about this election or not (the vast polls all being fundamentally off)?What exactly did he say in that article here that doesn't jive with you?
    I am not sure what you think "doesn't jive" with what I said. I told you I already read Silver's take, in fact I described exactly what it says. I am not sure what you have a problem with here? Silver admits that he will be wrong if the polls are wrong, which is what I said. He says that the odds of the polls being wrong are the odds he gives Romney of winning, which I already agreed with. He says that he is basing the odds the polls are wrong off of historical poll data and results.

    But this last step is the whole ball of wax. How many pollsters were there in 1976 vs today (Silver uses polls from 1968 on)? How many cell phones? Caller ID? Month or more long early voting windows that distort likely voter samples? African-American incumbents? This much partisanship? Blogs and Twitter? As much media bias? Elections 2 years after the biggest reversal the House has seen? Elections after an unpopular healthcare law was passed? The point is, these pollsters are in uncharted territory.

    And frankly I don't see how the two to three pollsters from 1972 that called on rotary phones during the evening news (shown on the three broadcast TV channels at the time) and their results should even enter the equation when trying to judge the accuracy of 2012 polling. Obviously there are differences in every election so pollsters do not need exact duplicate elections in order to be somewhat accurate. But there are potentially many more significant pitfalls around in this election in terms of trying to accurately gauge the electorate and how it will turn out and vote.

    And it isn't just wishful thinking about the polls being biased against Romney. There is anecdotal evidence and common sense on the side that things may not be as they seem according to the polls. The polls say the electorate will be similar to 2008. On the face of it, 2008 was a perfect storm for Democrats. Personable, hyped, fawned-over, African-American running against an old "moderate" Republican who barely was supported by his party, after a massive financial collapse that occurred on an unpopular Republicans "watch." Now we have the same guy but without the same fawning, a very dubious 4-year record, after a groundswell midterm that thoroughly repudiated the guys agenda vs. a Republican who is more electable than the last guy, even if not close to a great candidate. Now, do you think that the support and enthusiasm and turnout of both sides will mirror 2008? It is an honest question, because much of the polling indicates that this will in fact be the case.
    Last edited by Haloti92; 11-05-2012 at 01:17 AM.





  7. #163

    Re: RCP Electoral Map Thread

    were on the same page here. Where my response came from was in your mentioning about demographics and polls using 2008 info. In my opinion, Nate addressed that below, more specifically the bolded part:

    Polling is a difficult enterprise nowadays. Some estimate that only about 10 percent of voters respond even to the best surveys, and the polls that take shortcuts pay for it with lower-still response rates, perhaps no better than 2 to 5 percent. The pollsters are making a leap of faith that the 10 percent of voters they can get on the phone and get to agree to participate are representative of the entire population. The polling was largely quite accurate in 2004, 2008 and 2010, but there is no guarantee that this streak will continue. Most of the “house effects” that you see introduced in the polls — the tendency of certain polling firms to show results that are consistently more favorable for either the Democrat or the Republican — reflect the different assumptions that pollsters make about how to get a truly representative sample and how to separate out the people who will really vote from ones who say they will, but won’t.

    But many of the pollsters are likely to make similar assumptions about how to measure the voter universe accurately. This introduces the possibility that most of the pollsters could err on one or another side — whether in Mr. Obama’s direction, or Mr. Romney’s. In a statistical sense, we would call this bias: that the polls are not taking an accurate sample of the voter population. If there is such a bias, furthermore, it is likely to be correlated across different states, especially if they are demographically similar. If either of the candidates beats his polls in Wisconsin, he is also likely to do so in Minnesota.

    The FiveThirtyEight forecast accounts for this possibility. Its estimates of the uncertainty in the race are based on how accurate the polls have been under real-world conditions since 1968, and not the idealized assumption that random sampling error alone accounts for entire reason for doubt.





  8. #164

    Re: RCP Electoral Map Thread

    Quote Originally Posted by kojo View Post
    were on the same page here. Where my response came from was in your mentioning about demographics and polls using 2008 info. In my opinion, Nate addressed that below, more specifically the bolded part:

    Polling is a difficult enterprise nowadays. Some estimate that only about 10 percent of voters respond even to the best surveys, and the polls that take shortcuts pay for it with lower-still response rates, perhaps no better than 2 to 5 percent. The pollsters are making a leap of faith that the 10 percent of voters they can get on the phone and get to agree to participate are representative of the entire population. The polling was largely quite accurate in 2004, 2008 and 2010, but there is no guarantee that this streak will continue. Most of the “house effects” that you see introduced in the polls — the tendency of certain polling firms to show results that are consistently more favorable for either the Democrat or the Republican — reflect the different assumptions that pollsters make about how to get a truly representative sample and how to separate out the people who will really vote from ones who say they will, but won’t.

    But many of the pollsters are likely to make similar assumptions about how to measure the voter universe accurately. This introduces the possibility that most of the pollsters could err on one or another side — whether in Mr. Obama’s direction, or Mr. Romney’s. In a statistical sense, we would call this bias: that the polls are not taking an accurate sample of the voter population. If there is such a bias, furthermore, it is likely to be correlated across different states, especially if they are demographically similar. If either of the candidates beats his polls in Wisconsin, he is also likely to do so in Minnesota.

    The FiveThirtyEight forecast accounts for this possibility. Its estimates of the uncertainty in the race are based on how accurate the polls have been under real-world conditions since 1968, and not the idealized assumption that random sampling error alone accounts for entire reason for doubt.
    Yeah, I don't think we were ever on completely different pages, but again, that bold part doesn't tell us anything meaningful. He says he "accounts for" the possibility that the polls are off by looking at how much they have been off in the past. But the distant past is only marginally meaningful at best, imo, and meaningless at worst, imo. The recent past is another matter but then we have the problem of insignificant sample sizes, probably 2000, 2004, 2008 only, and 2000 had the late-DUI effect which Silver just ignores. And 2008 had the unprecedented "perfect" storm for Democrats. Like I said, I don't think the way Silver says he "accounts for" the possibility of the polls being off means much in terms of their actual chances of being off.

    I would much prefer some kind of rationale that specifically addresses (in terms of reasoning, i.e. why and how) the discrepancy between the tight national polls, the almost even party-ID when polled specifically, and the less-tight battleground states, and uneven party-IDs being found in these states.

    For example the most recent PPP polls for Ohio and Virginia that came out today. Shows sample of D+8 in Ohio; when 2004 was R+5 and 2008 was D+8. And it gives Obama a 5 point lead. Then there is the Virginia poll which shows sample of D+5; when 2004 was R+4 and 2008 was D+6. And gives Obama a 4 point lead. If you split the difference between the two turnouts, Romney is ahead in both polls. If it is 2004 turnout (which due to demographics is fairly unlikely, imo) then Romney wins by several points.

    To me, those polls and their results seem extremely unlikely, yet there they are, and there they get put into Silver and Wang's models along with many like them. Could they be dead on? Sure. Do they seem strange to me in terms of a common sense comparison of the situations at election time of 2004, 2008 and now? Yes, to me, they do, even if they are eventually proven to have been accurate.





  9. #165
    Join Date
    Aug 2007
    Location
    Houston, TX Y'all
    Posts
    34,414
    That might be the best exchange this forum has seen in quite some time. Kudos!

    By the way, Obama pulls back even in Gallups latest.





  10. #166

    Re: RCP Electoral Map Thread

    Quote Originally Posted by Haloti92 View Post
    Yeah, I don't think we were ever on completely different pages, but again, that bold part doesn't tell us anything meaningful. He says he "accounts for" the possibility that the polls are off by looking at how much they have been off in the past. But the distant past is only marginally meaningful at best, imo, and meaningless at worst, imo. The recent past is another matter but then we have the problem of insignificant sample sizes, probably 2000, 2004, 2008 only, and 2000 had the late-DUI effect which Silver just ignores. And 2008 had the unprecedented "perfect" storm for Democrats. Like I said, I don't think the way Silver says he "accounts for" the possibility of the polls being off means much in terms of their actual chances of being off.

    I would much prefer some kind of rationale that specifically addresses (in terms of reasoning, i.e. why and how) the discrepancy between the tight national polls, the almost even party-ID when polled specifically, and the less-tight battleground states, and uneven party-IDs being found in these states.

    For example the most recent PPP polls for Ohio and Virginia that came out today. Shows sample of D+8 in Ohio; when 2004 was R+5 and 2008 was D+8. And it gives Obama a 5 point lead. Then there is the Virginia poll which shows sample of D+5; when 2004 was R+4 and 2008 was D+6. And gives Obama a 4 point lead. If you split the difference between the two turnouts, Romney is ahead in both polls. If it is 2004 turnout (which due to demographics is fairly unlikely, imo) then Romney wins by several points.

    To me, those polls and their results seem extremely unlikely, yet there they are, and there they get put into Silver and Wang's models along with many like them. Could they be dead on? Sure. Do they seem strange to me in terms of a common sense comparison of the situations at election time of 2004, 2008 and now? Yes, to me, they do, even if they are eventually proven to have been accurate.
    Right and Nate doesn't weigh all Polls the same, so how he decides which individual poll is debatable. He has an article called "house effects" where he explains and ranks which polls are more biased and then says that he reduces/increases their effect in his calculations so yes, PPP won't have the same influence as say Susquehanna since it is blatantly left leaning. If you guys think mitt is going to eek this one out you may want to put some money up on intrade, the returns on there look crazy. Last I checked Obama was a 64% favorite. Other gambling sites, especially the euro ones have him in the high 70s...





  11. #167
    Join Date
    Apr 2009
    Posts
    13,453
    Blog Entries
    5

    Re: RCP Electoral Map Thread

    Looks like Billy got the evangelicals moving at least in OHio where he took out a
    1-page ad.

    Coal miners keep turning out in the early voting along with the evangelicals.
    There have been long lines of voters in the early voting.

    A GOP minority congressman in FLA and former US Army Colonel said Libya is coming into play this late in the game and a lot of people in FLA feel OBY isn't protecting our people overseas. He said some counties still have a hi unemployment rate above 9%.

    He sees a Mitt win there.





  12. #168
    Join Date
    Apr 2009
    Posts
    13,453
    Blog Entries
    5

    Re: RCP Electoral Map Thread

    While OBY is desperate asking his people to vote for revenge, Rasmussen now has
    Mitt up by +1.

    OBY is one desperate man.

    http://www.drudgereport.com/


    Mitt has double digit leads in independents from 22-60% even in Ohio just as Dick
    said he would get all summer

    So you can't depend on a lot of these polls.
    Last edited by AirFlacco; 11-05-2012 at 10:47 AM.





Bookmarks

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  
Link To Mobile Site
var infolinks_pid = 3297965; var infolinks_wsid = 0; //—->