1. #261
    You seriously don't understand why it would be more impressive to predict an even a year ahead of time vs a couple of days?
    The job of a poll isn't to predict the future, unless they're specifically asking about a future event, they're about measuring exactly what public opinion is at a specific point in time. That's why you see a lot of polling questions with stuff like "if the election were held tomorrow..." and such. You then use a series of polls to predict the future. Good polling is like digging core samples when you're looking for coal. You go along an area digging holes and use the data you get to predict trends.

    As such there isn't much value in polls that try to predict events too far out. Whether those polls end up being accurate or not is irrelevant and to hold up the results as proof of their merit is just a selection fallacy, since you're only using single polls at a time.

    If we are going to debate the quality of their polling though this is a pretty big deal: http://fivethirtyeight.blogs.nytimes...rmed-strongly/

    Rasmussen's polling was the farthest off the across the board in the last major election. I mean they had 13 polls off by more than 10%, and one off by 40%

    On top of that their methodology leaves a lot to be desired.
    Last edited by Wells; 2012-02-12 at 02:09 AM.

  2. #262
    eliminate international drug programs
    substantially reduce foreign travel
    eliminate international organizations and commissions

    Thats Ron Paul, pretty much going isolating mode. blech.
    I am the King of Rome, and above grammar.
    - Sigismund, Holy Roman Emperor


  3. #263
    Quote Originally Posted by Felya420 View Post
    Why should I take it up with anyone, but you? You were the one who backed up the accuracy of a poll during a primary, with one in a presidential election... days before the actual vote... I think it's an invalid comparison...
    Show me where I backed up the accuracy of a poll during a primary with one in a presidential election. Please.

    Wells response to you shows you why I said to take it up with him.You guys have differing opinions on it. And I seem to have predicted it successfully since he took it up with you in the very next post.
    Quote Originally Posted by Wells View Post
    The job of a poll isn't to predict the future...
    Quote Originally Posted by Felya420 View Post
    The fact that you don't know when it's from should really speak for it self. .
    Quote Originally Posted by Merkava View Post
    I don't know. Final poll, within a couple days of the election I'm guessing.
    I said that and then provided a link which is here http://www.realclearpolitics.com/bush_vs_kerry_hth.html
    So I answered your question and then provided proof. Please take the time to read what I say before responding.

    Quote Originally Posted by Felya420 View Post
    How is giving data for Bush vs Kerry a few days before the actual election, an example of accuracy during a primary poll, where a candidate is not even declared?
    I wasn't defending the accuracy of a primary poll. I was answering Wells when he said this...
    Quote Originally Posted by Wells View Post
    A single polling event is not enough to draw your conclusion from.
    Thanks for participating but please take the time to read the thread a little before responding. I put the effort into quoting what I'm responding to, the least you can do is read it.

    ---------- Post added 2012-02-12 at 12:57 AM ----------

    Quote Originally Posted by Wells View Post
    No. A pollster's job is to accurately predict the mood of the public at a given time. If they happen to hit the same mark a month earlier that ends up being the final election count that doesn't mean they're doing their job better, it just means they're getting lucky.
    Sure, you're right on that one. Maybe I should have made myself clearer. I was talking about Rasmussen's performance in the presidential general election polling. You said a single event isn't enough to draw a conclusion from. I linked a second one. And gave the dates. I'm not defending criticisms of Rasmussen's conservative bias, I think more often than not that's probably true. But Rasmussen Reports has only been around since 2003. I'm not saying he's right, or his methodologies aren't questionable, just that he was pretty good on the last two presidential elections. I don't know how close he was to every other pollster 8 months out this time in 2008 and in 2004.

    I brought up the point that Rasmussen's final poll on Bush Kerry 2004 was very accurate and you said this in return...
    Quote Originally Posted by Wells View Post
    One of the more common problems with Rasmussen actually is they do their "final polling" much farther back from the actual date than many other groups.
    and I posted this link http://www.realclearpolitics.com/bush_vs_kerry_hth.html. Do you care to address that?
    Last edited by Merkava; 2012-02-12 at 07:00 AM.

  4. #264
    Again, you're missing the point I was responding to, where someone used Rasmussen to determine "center" and declared everyone else to the left.

  5. #265
    Quote Originally Posted by Wells View Post
    Again, you're missing the point I was responding to, where someone used Rasmussen to determine "center" and declared everyone else to the left.
    Point taken.

    I brought up the point that Rasmussen's final poll on Bush Kerry 2004 was very accurate and you said this in return...
    Quote Originally Posted by Wells View Post
    One of the more common problems with Rasmussen actually is they do their "final polling" much farther back from the actual date than many other groups.
    and I posted this link http://www.realclearpolitics.com/bush_vs_kerry_hth.html. Do you care to address that?

  6. #266
    I brought up the point that Rasmussen's final poll on Bush Kerry 2004 was very accurate and you said this in return...
    Rasmussen was a much better organization in the past. In 2004 and to a lesser extent 2006/08 their polling was fine. Not the best out there, but ok. In 2010 they managed to somehow be one of the worst.

    Polling organizations are a little like a car. It doesn't matter how well it ran in the past, if it runs like shit now its shit.

    That being said, happening to get the "correct" data doesn't mean their methodology is any less shitty. I mean last I checked they weren't even calling cell phones and conducted all calls for a poll within the same 4 hour window.

  7. #267
    I don't think there's a shadow of a doubt that Obama's gonna be seeing a second term.
    Quote Originally Posted by High Overlord Saurfang
    "I am he who watches they. I am the fist of retribution. That which does quell the recalcitrant. Dare you defy the Warchief? Dare you face my merciless judgement?"
    i7-860 @2.8GHz | Radeon HD 7770 | 8GB DDR3-1333MHz | Corsair CX 430W |

  8. #268
    Quote Originally Posted by Wells View Post
    Rasmussen was a much better organization in the past. In 2004 and to a lesser extent 2006/08 their polling was fine. Not the best out there, but ok. In 2010 they managed to somehow be one of the worst.

    Polling organizations are a little like a car. It doesn't matter how well it ran in the past, if it runs like shit now its shit.

    That being said, happening to get the "correct" data doesn't mean their methodology is any less shitty. I mean last I checked they weren't even calling cell phones and conducted all calls for a poll within the same 4 hour window.

    I brought up the point that Rasmussen's final poll on Bush Kerry 2004 was very accurate and you said this in return...
    Quote Originally Posted by Wells View Post
    One of the more common problems with Rasmussen actually is they do their "final polling" much farther back from the actual date than many other groups.
    and I posted this link http://www.realclearpolitics.com/bush_vs_kerry_hth.html. Do you care to address that?

    You made a statement. You are now being asked to provide evidence to support that statement.

  9. #269
    Silver also criticized Rasmussen for often only polling races months before the election, which prevented them from having polls just before the election that could be assessed for accuracy. He wrote that he was “looking appropriate ways to punish pollsters” like Rasmussen in his pollster rating models who don’t poll in the final days before an election.
    http://www.fivethirtyeight.com/2010/...ight-live.html

    The problem you're having here is you're taking a single election and only that one into account, making the same mistake that last guy did. Its like trying to draw advertising rate trends in NFL games and only looking at the Super Bowel.

  10. #270
    Quote Originally Posted by Wells View Post
    http://www.fivethirtyeight.com/2010/...ight-live.html

    The problem you're having here is you're taking a single election and only that one into account, making the same mistake that last guy did. Its like trying to draw advertising rate trends in NFL games and only looking at the Super Bowel.
    Ok. I'm going to walk you through this. Very...slowly. Try to follow.

    I originally said this..
    Quote Originally Posted by Merkava View Post
    You want another presidential election? In 2004 Bush got 50.7% of the vote and Kerry got 48.3%. The final Rasmussen poll had Bush at 50.2% and Kerry at 48.5%
    You replied with this...
    Quote Originally Posted by Wells View Post
    One of the more common problems with Rasmussen actually is they do their "final polling" much farther back from the actual date than many other groups.
    Then...I linked to http://www.realclearpolitics.com/bush_vs_kerry_hth.html which shows that Rasumessen's final polling for Bush and Kerry in 2004 (which was a presidential race by the way) was over the same dates as every one else.

    Here's your problem. The link you provided shows Silver criticizing Rasmussen for not doing a poll in the last 4 weeks of the 2010 McCain-Hayworth Republican primary for senate. Too bad, since you were replying to my statement concerning Rasmussen polling for a presidential general election in 2004, which was six years earlier, lol.

    It's like me saying that a guy was a great World Series pitcher 6 years ago, and you tell me that can't be true because his regular season ERA is terrible today. Your link does absolutely nothing to back up your claim.

    Care to try again?
    Last edited by Merkava; 2012-02-12 at 09:09 AM.

  11. #271
    I was talking about methodology problems Rasmussen has. Silver didn't say this problem was constrained to a single election cycle. If you wanna go full Merkava mode I really don't give a shit, especially with you taking up your same tone. Its completely outside the point I was making, which you have been rather happy to drop in your usual fashion.

    Shit, I even said Rasmussen was a better organization in 2004. Nor did I say their polling in this specific race, the one that's completely irrelevant was a case of such a delay.

    What did happen was you made an assumption on when one of their polls was done and I pointed out that in some cases Rasmussen does not conduct their polling in the time period you would expect. Pedantry and whining ensued.
    Last edited by Wells; 2012-02-12 at 09:12 AM.

  12. #272
    Quote Originally Posted by Wells View Post
    I was talking about methodology problems Rasmussen has. Silver didn't say this problem was constrained to a single election cycle. If you wanna go full Merkava mode I really don't give a shit, especially with you taking up your same tone. Its completely outside the point I was making, which you have been rather happy to drop in your usual fashion.

    Shit, I even said Rasmussen was a better organization in 2004.
    Scott Rasmussen isn't my dad, lol. You don't score points by saying something good about Scott Rasmussen.

    The problem is this; You only know what you read on Wikipedia. You read the Silver Criticism portion of the Rasmussen Reports Wikipedia entry, and assumed you could make the argument that Rasmussen ends polling earlier fit into the discussion. If you had read the link you posted then you wouldn't have made the statement in the first place.

    When I said this
    Quote Originally Posted by Merkava View Post
    You want another presidential election? In 2004 Bush got 50.7% of the vote and Kerry got 48.3%. The final Rasmussen poll had Bush at 50.2% and Kerry at 48.5%
    There's no way in hell you would have replied with this
    Quote Originally Posted by Wells View Post
    One of the more common problems with Rasmussen actually is they do their "final polling" much farther back from the actual date than many other groups.
    because the Nate Silver quote from 2010 was "Rasmussen -- which polled the McCain-Hayworth primary eight times in a race where there was some disagreement among pollsters -- was not willing to do so during the final four weeks of the campaign"

    You fell into a common Wikipedia trap; you failed to read the references.

    Quote Originally Posted by Wells View Post
    What did happen was you made an assumption on when one of their polls was done.
    LOL. I made no assumption. I didn't know the exact date, I don't have the 2004 calendar memorized. Sorry if I can't recall exactly when the first Tuesday after the first Monday in November falls every four years. But you know what? I provided a reference that backs up my claim exactly.

    Quote Originally Posted by Wells View Post
    I pointed out that in some cases Rasmussen does not conduct their polling in the time period you would expect.
    Get this straight. I was talking about a presidential election in 2004. The link you provided addresses one example from a senate primary six years later.

    Quote Originally Posted by Wells View Post
    Pedantry and whining ensued.
    I won't even respond. Except to say that I won't respond. And to clarify that response, and uh...
    Last edited by Merkava; 2012-02-12 at 09:35 AM.

  13. #273
    The problem is this; You only know what you read on Wikipedia. You read the Silver Criticism portion of the Rasmussen Reports Wikipedia entry, and assumed you could make the argument that Rasmussen ends polling earlier fit into the discussion. If you had read the link you posted then you wouldn't have made the statement in the first place.
    I'm curious how you think you can read my mind. I've said in the past I'm a huge fan of Nate Silver and follow him pretty damn closely, thus am aware of the flaws in Rasmussen's methodology. I dug the link up from wikipedia yes, but if you think this even resembles a valid attack that's pretty funny.


    When I said this
    That's not what I was replying too.

    This is the actual post: http://www.mmo-champion.com/threads/...1#post15439172

    From it you can see what I was responding to was this: "I don't know. Final poll, within a couple days of the election I'm guessing."

    Pointing out that Rasmussen methodology doesn't always follow your assumption is rather valid and that you've drug us off on this stupid tangent is sad but expected.

    LOL. I made no assumption.
    See above.

  14. #274
    Mechagnome ThatInternet's Avatar
    Join Date
    Oct 2011
    Location
    Shrine of Talos
    Posts
    645
    Quote Originally Posted by Flaks View Post
    I don't think there's a shadow of a doubt that Obama's gonna be seeing a second term.
    yeah, I don't think any of the republican candidates can trump obama.
    dictated but not read.

  15. #275
    Quote Originally Posted by Wells View Post
    That's not what I was replying too.

    This is the actual post: http://www.mmo-champion.com/threads/...1#post15439172

    From it you can see what I was responding to was this: "I don't know. Final poll, within a couple days of the election I'm guessing."
    .
    So you didn't know what final poll I was referring to? That's your only defense at this point. Because if you knew that I was referring to a presidential poll from 2004 you wouldn't have attempted to counter that with evidence from one race, a republican senate primary that happened six years later.

    Again, there was no assumption. I didn't know the exact date and I said so. But it was from the last week before the election. See, the links I provide actually support my statements.

  16. #276
    What I was doing was correcting your assumption that the poll came from just prior to the election. Not very complicated, and hardly worth this tangent.

  17. #277
    Quote Originally Posted by Wells View Post
    What I was doing was correcting your assumption that the poll came from just prior to the election. Not very complicated, and hardly worth this tangent.
    Agreed. So the question to you is this,
    So you didn't know what final poll I was referring to? That's your only defense at this point. Because if you knew that I was referring to a presidential poll from 2004 you wouldn't have attempted to counter that with evidence from one race, a republican senate primary that happened six years later.

  18. #278
    What is your problem? I've already explained to you everything you need to know. I'm not interested in you trying to score epoints. You made a faulty assumption and I pointed it out. Don't get huffy.

    And Silver didn't say their delays were in only one race, thanks. In fact that wouldn't even make sense.
    Last edited by Wells; 2012-02-12 at 10:07 AM.

  19. #279
    Quote Originally Posted by Wells View Post
    What is your problem? I've already explained to you everything you need to know. I'm not interested in you trying to score epoints.

    And Silver didn't say their delays were in only one race, thanks.

    Did he say Rasmussen did it in the 2004 general election? Because that's the issue.

    You've explained nothing. As usual. You've danced, evaded, moved the goalposts, attempted to construct strawmen, used profanity, questioned my motives, accused me of whining. The only thing you have left to do is appeal to a moderator for help, which I'm sure is imminent. My problem, since you asked, is that you attempted to appear knowledgeable because you read a Wikipedia entry. You knew I was referring to a 2004 presidential general election. What you didn't know is that your criticism of Rasmussen was based on a 2010 senate primary. Because you didn't read it. No one that read it would have attempted to use it as a defense. Six years later?!? LOL. Oh, the seafood at that restaurant couldn't have been good six years ago, because my girlfriend had a bad steak there last night. Sorry if you think my tone a tad scurrilous, but your explanations are just that ridiculous.

    Edit. You may find this interesting. http://www.realclearpolitics.com/epo...168.html#polls
    It doesn't appear much of anyone was doing any polling in that race in the last four weeks. I wonder if Nate was as tough on Magellan, PPP, and DailyKos as he was on Scott. I'm guessing not. But that's ok, because you've got lot's of other examples, right?
    Last edited by Merkava; 2012-02-13 at 12:36 AM.

  20. #280
    I love how you think you can read my mind. You made a bad assumption. I corrected you. Not complicated. So can we get back to discussing something of value? Like 2012 polling?

    And don't criticize me for not reading my links when you didn't. Silver was talking about finding a way to punish any polling agency that didn't poll close enough to the date.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •