Skip to main content

View Diary: So, about that CNN Snap Poll (290 comments)

Comment Preferences

  •  Great catch . . . (15+ / 0-)

    However, the poll may still be representative of registered voters who watched the debate.  It just means that the debate audience wasn't very representative of the electorate as a whole.  

    It was telling that the poll trended whiter, older, more conservative, more Republican and more southern than the electorate as a whole as measured in presidential preference polls.

    I'll be curious to see the what the ratings numbers look like over the next few days. Also it will be interesting to see what kind of impact this has on presidential polls.

    •  This is true. (11+ / 0-)
      However, the poll may still be representative of registered voters who watched the debate.  It just means that the debate audience wasn't very representative of the electorate as a whole.
      In which case the debate won't matter that much.

      Have you googled Romney today?

      by fou on Wed Oct 03, 2012 at 11:08:05 PM PDT

      [ Parent ]

    •  True, might've been quick to attack the sample but (10+ / 0-)

      I don't recall these snap polls being that unrepresentative of the electorate last time, even accounting for the fact that Democratic enthusiasm was higher in '08.

      Of course, if the debate audience this year just happens to be like that, that's just fine with me.  A non-game changing Romney win in a given debate should move the needle even less than I originally thought.

      •  This is a bit like the controversy . . . (8+ / 0-)

        that conservatives have raised about party affiliation in national polls.

        Presidential preference and party affiliation are variables that pollsters want to measure.  You weight fixed variable in order to ensure that the poll is representative of the likely electorate.

        In this case, the demographic composition of the debate audience is a variable that changes.  The universe of debate watchers is not a synonym for "the voting electorate".  It's a subset with its own characteristics.  

        I don't think this is a game-changer, but I don't think it hurts Romney either.  Probably helps him on the margins -- shores up his existing support, maybe wins him some undecideds.  It'll be interesting to see the national polls over the next few days.

        •  good job,,, (2+ / 0-)
          Recommended by:
          NotGeorgeWill, congenitalefty

          well actually excellent analysis!!!

        •  Right, in this polling situation, you just have to (3+ / 0-)

          go with the sample you get, even if it seems off.  

          But not to sound like the nutjob unskewing crowd - it just seems very unusual that so few of Obama's base demographic supporters were watching.  But perhaps it is so.

        •  To be fair (9+ / 0-)

          It's not like that contravesery as much as you say. At issue in the "poll unskewing" fiasco is that people self-report Dem, Rep, or Ind based on their voting inclination, which tends to be fluid. This poll seems to have left out large swaths of the population at large. I highly doubt the vast majority of debate watchers are white seniors, or steadily approaching seniority, who live exclusively in the South.

          •  Yes, I thought age and region don't float... (1+ / 0-)
            Recommended by:
            biscobosco

            like party ID but instead go to whether the unchanging characteristics of a sample is representative of a larger population.

            •  What is the population that is being measured? (3+ / 0-)
              Recommended by:
              fou, Bob Duck, congenitalefty

              We aren't looking for a representative sample of the electorate.  We are looking for a representative sample of TV audience that watched the debate.

              The characteristics of a viewing audience for a debate may not correspond exactly or even closely with the electorate as a whole.  

              So as a population, the GOP skew may be representative.  It isn't representative of the voting population.  It is representative of the audience that bothered to watch the debate.

              •  well, lets just pick on "white" (3+ / 0-)
                Recommended by:
                wishingwell, sharman, wu ming

                For example Nielsen has:
                " Key Nielsen findings include:

                Nearly 43 percent of Hispanic homes watched the common, primetime coverage of the Democratic National Convention, while 35 percent tuned in to the Republican National Convention."

                So, strangely,   all of those Hispanics who were so eager to watch conventions simulataneously turned off their TVs for the debates. The sample was ALL WHITE.

                And as I said above, OFA had 4000 debate watch parties nationwide.. While Romney had 300+ ??

                Interesting.

                "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                by biscobosco on Thu Oct 04, 2012 at 12:18:10 AM PDT

                [ Parent ]

                •  It will be interesting to look at the Nielsen (1+ / 0-)
                  Recommended by:
                  biscobosco

                  numbers for the debates.

                  I don't take N/A for most categories to mean "all white".  I take the N/A to mean that there weren't enough respondents in the other subgroups to provide a statistically reliable percentage.  In the context of the national audience, however, the views may still be representative.

            •  Personally I never ever watch a debate (2+ / 0-)
              Recommended by:
              sharman, highacidity

              In Arizona. I always fly to Alabama first.

              "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

              by biscobosco on Thu Oct 04, 2012 at 12:13:20 AM PDT

              [ Parent ]

          •  What appears to have happened . . . (4+ / 0-)

            in cases where there is no margin of error reported, is that the number of respondents was too small.  It isn't necessarily a question that the vast majority of watchers were older, whiter, southern, Republicans.  It may just mean that a near majority of respondents were from the regions and that in other parts of the country fewer people were paying attention to the debates  Pretty small sample for a national poll too -- think it was just about 600 people.

            •  I see what you're saying now (1+ / 0-)
              Recommended by:
              NotGeorgeWill

              After giving it some thought. It was 430 respondents, so low sample size anyway. It also strikes me, purely from experience after living in Jersey, NYC, and North Carolina that older southerners may be more inclined to politely accept a second bothersome phonecall from a survey late at night than the overall population may. Not nefarious, but I certainly think it gives a false impression of the debate results.

        •  Excuse me (2+ / 0-)
          Recommended by:
          biscobosco, wishingwell

          How hard is it to get a geographically diverse sample?  The area codes are a very big clue.

          •  It isn't hard to get a geographically . . . (1+ / 0-)
            Recommended by:
            HudsonValleyMark

            diverse sample.

            But it may be that they conducted a poll and had a high non-response rate in other regions.  Whereas in the south, there was more interest in the debate, people not only watched the event, but were more willing to share an opinion.

            If the goal is to measure reactions in a particular region, then you focus on that population.  If the goal is to get a snapshot of the national audience, you poll the entire nation.  It may turn out that the national audience is heavily concentrated in one particular region -- it isn't concentrated across regions.  In fact, that's what the snap poll seems to suggest.

            The response rates in regions outside of the south may have been too low to provide a statistically reliable picture at the regional level.  But it may still be statistically representative of the national audience.

            If they had polled 1,200 people instead of 600 nationally, perhaps they would would have had enough data to make a judgment about views in particular regions.  

            •  that's what you're going with? (3+ / 0-)
              Recommended by:
              biscobosco, wishingwell, wu ming

              They actually called an equal number of phone numbers in all areas of the country, and only the southerners answered their phones?

              •  yeah pretty bogus (0+ / 0-)

                "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                by biscobosco on Thu Oct 04, 2012 at 12:27:46 AM PDT

                [ Parent ]

              •  Not just answer the phone (2+ / 0-)
                Recommended by:
                NotGeorgeWill, wishingwell

                But be willing to share their opinions about the presidential race to a pollster and also to be willing to be called again after the debate. I think, after reading through the posts, ORC may have inadventently introduced a bias based on southern hospitality, if you believe in such things.

                •  Yes as just today a friend told me his daughter (0+ / 0-)

                  is very liberal , was against fracking , but said the Texans were her best and most polite customers and left big tips too. They were all wingnuts who would sit and bash Obama and love themselves some fracking and big oil but they were extremely polite and kind to everyone in the restaurant and treated the staff like gold.

                  Follow PA Keystone Liberals on Twitter: @KeystoneLibs

                  by wishingwell on Thu Oct 04, 2012 at 12:51:19 AM PDT

                  [ Parent ]

              •  No, that's your misinterpretation . . . (0+ / 0-)

                of what I am saying.

                Actually I see the total number of polled respondents was actually less than 400.

                What this means is that you could have 20 people from a given minority group in a given region providing a response.  However, the response pool is too small to provide a reliable statistical measure.

                I am saying that out of a relatively small sample, the poll seems to suggest that they had enough responses in the South amongst white respondents to provide sub-category numbers that are statistically meaningful.  Even in those cases the margin of error is something like +/- 9 points.  

                •  That's a little generous (0+ / 0-)

                  Judging by the margins of error, the sample was about 90% white to 10% 'not-white'. It's not that they didn't have enough people of any given minority to get data from: they didn't have enough of all minorities combined to get decent data!

                  (It was also roughly 80% 50-and-over, which is also pretty insane.)

              •  Yes that would be strange as granted the older (0+ / 0-)

                crowd that would be my parents friends and siblings always answer their phone. I never get their machines.  
                We are mid 5oish and always check the caller ID first.

                Then there is my son, nephew who are in their 30s and seldom answer their phones and only have cell phones.

                But there are people like my aunt in PA and my aunt in OH would always answer their phone and watched the debate.

                It is too strange to think that even if they only surveyed all people over 50, only southerners would answer their phone. They sure missed all my relatives and most of the rest of yours too....

                Follow PA Keystone Liberals on Twitter: @KeystoneLibs

                by wishingwell on Thu Oct 04, 2012 at 12:49:48 AM PDT

                [ Parent ]

              •  but the regions aren't equal (0+ / 0-)

                There doesn't even have to be non-response bias to explain the result.

                Even in a perfectly representative sample of 430 U.S. adults, broken into four regions of which the South is substantially the largest, there's a good chance that the other three will end up with fewer than 100 respondents each.

                Election protection: there's an app for that!
                Better Know Your Voting System with the Verifier!

                by HudsonValleyMark on Thu Oct 04, 2012 at 03:38:21 AM PDT

                [ Parent ]

        •  I just dont believe that 99% of everyone (2+ / 0-)
          Recommended by:
          wishingwell, wu ming

          who watched the debates lives in the south and is over 50 and white.  It has a feel of falsity.  

          Especially when I see headlines like

          Obama Campaign Sponsoring More Than 4000 Debate Watch Parties Nationwide, Compared to Romney’s 336
          Maybe this cheat is the october surprise! :)

          "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

          by biscobosco on Thu Oct 04, 2012 at 12:11:58 AM PDT

          [ Parent ]

          •  If they called landines, we were not home, we (0+ / 0-)

            were at watch parties, a lot of people were.

            That would skew things too as I bet CNN called landlines exclusively and first of all, someone has to be willing to be pick up the phone after 10 pm and be wiling to take a survey at that takes time. Sometimes I do polls and surveys and sometimes I have no time at all and on my way out the door.

            Follow PA Keystone Liberals on Twitter: @KeystoneLibs

            by wishingwell on Thu Oct 04, 2012 at 12:53:10 AM PDT

            [ Parent ]

          •  That's not an accurate interpretation . . . (1+ / 0-)
            Recommended by:
            HudsonValleyMark

            N/A could mean that they can produce a number for the South because they had say 80 to 90 respondents, which offer a +/- 9 percent margin of error.  However, in the northeast maybe they only had 50 respondents in a region that has a larger population, so the views are reported as "N/A" because they are not sufficient to provide a statistically valid representative sub-category percentage.

            I think it is accurate to say, based on the numbers that the viewing audience skewed Republican and southern.

            Does that mean 100 percent, or 99 percent?  No.  Maybe it accounted for 35-40 percent of the viewing audience.  Obviously that is not representative of what the electorate will look like.  The poll was not measuring opinions for the entire voting population.  It was measuring opinions of the people who are registered voters who watched the debate.

            Using debate parties as a proxy for the national audience is an even less reliable measure.

            e.g.the overwhelming majority of Americans probably watched the debates at home with family, not at viewing parties.  There are probably characteristics of the viewing parties that are not representative of the national debate audience in other ways.  The only thing that the numbers suggest with the viewing parties is that Obama supporters were more likely to have viewing parties (that they registered with some campaign website).  You can't use it as a proxy for making generalizations about a larger audience.  This is an illustration of the fallacy of composition.  

            •  OK, but here's my concern (1+ / 0-)
              Recommended by:
              wishingwell

                I think it would behoove CNN to release the entire set of demographics for the poll.

              It's not clear to me that the sample is truly a random sample of those who watched the debates.   So let me see If I get your argument right. Let's just look geography.

              Ok, roughly us pop, 60 Million NE, 60 Million Midwest 100 Million West, 110 million South (not sure if Texas is included)

              It is bizzare to me that they did not sample enough people in the West, and the midwest, and the east to get an amount within a decent margin of error.

              So, lets figure out how many would be the most they could get and not report because MOE too big?  I'm not positive, but how's this

              you say 80-90 is enough? so would 70 be too few? So that would mean 70 in the West, 70 Midwest, 70 NE.

              = 210 - So that means that 390 were from the South. That seems almost double what you would expect as a percentage of population.

              Let me know your response.

              "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

              by biscobosco on Thu Oct 04, 2012 at 01:29:31 AM PDT

              [ Parent ]

              •  try this (0+ / 0-)

                2008 exit poll: 21% northeast, 23% west, 24% midwest, 32% south. So, with 430 respondents, they are at best scraping 100-per-region outside the south. I don't know exactly what cutoff they used, but 100 -> MOE 10%. 80-90 is even bigger.

                These numbers just don't look far off, in that respect.

                With a snap poll, there will always be problems getting a really representative sample; they could spend 3x as much, get their MOEs down (and have more crosstabs to report), but not have materially more informative results.

                Maybe post-debate snap polls shouldn't be reported at all. But, to be honest, a lot of people here enjoyed them in 2004 (I was only lurking then) and 2008.

                Election protection: there's an app for that!
                Better Know Your Voting System with the Verifier!

                by HudsonValleyMark on Thu Oct 04, 2012 at 03:44:11 AM PDT

                [ Parent ]

                •  Not just geographic demographics (0+ / 0-)

                  There is no information in the poll internals as to percentage of women, minorities, youth, etc surveyed. We are pretty sure that this poll was not a representative sample of US voters, but we don't know more about the race, gender, age, demographics to compare it to other polls.

                  "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                  by biscobosco on Thu Oct 04, 2012 at 08:54:58 AM PDT

                  [ Parent ]

              •  Prob 100-125 from the south out of 430 (0+ / 0-)

                MoE calculator

                The poll had 430 respondents, indicating 4.7% MoE, but the pollsters rounded the MoE to the nearest .5%, so 4.5%.
                For the south, 8.5% indicates 100-125 respondents, not too far out of whack. Over 50 was 5.5%, which would mean a minimum of 290, or 67% of the population. so that is more seriously skewed.

                Disclaimer: If the above comment can possibly be construed as snark, it probably is.

                by grubber on Thu Oct 04, 2012 at 05:33:19 AM PDT

                [ Parent ]

        •  no no no no no. you have it backwards. (5+ / 0-)
          Recommended by:
          wishingwell, Seneca Doane, elmo, askew, wu ming

          Presidential preference and party affiliation are variable. But that's not the complaint. The complaint is that NON-variable factors like region, race, gender, and age are 100% weighted here.

      •  YEAH BUT (11+ / 0-)

        Headlines blare that Romney wiped the floor with O, won by 40 points.

        And thus create the lying perception that Romney presented a very credible case, and Obama couldn't defend himself.

        That is some dirty propaganda at work there.  

        •  Fair point . . . (3+ / 0-)
          Recommended by:
          wishingwell, MHopeful, Larsstephens

          if the composition of the audience skews Republican, then what the polls are really showing is that Romney bested Obama in front of a Republican leaning audience.

          Huge shocker?  Not really.

          Part of reporting facts, is to report them in context.  So, assuming that the interpretation is correct that there was a GOP skew -- and that I'm not simply misreading the data set -- the skew should be reported as such along with the top-line number.

          •  A 10 or even 15% skew (4+ / 0-)

            might reflect a self-selection bias--more Rs watched than Ds.  A 90% skew, all in R-favorable demographics, simply stinks.

            •  Yes, (2+ / 0-)
              Recommended by:
              wishingwell, Larsstephens

              It doth have a stench, methinks.

              "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

              by biscobosco on Thu Oct 04, 2012 at 12:30:29 AM PDT

              [ Parent ]

            •  Not sure where you are getting a (0+ / 0-)

              90 percent skew.

              The composition of the viewing audience skewed GOP by about 15 percent relative to national polls.  Romney's favorables were about 15-20 percent higher.  

              All of that points to the idea that the audience was unrepresentative of the electorate as a whole.

              This is entirely possible.  Maybe people who are committed to Obama wanted to watch other programming (or not watch TV at all).  There was no new information that they needed to see in order to make a judgment about the race, and they aren't political junkies like us who watch simply to see how our guy performs.

          •  NO (2+ / 0-)
            Recommended by:
            wishingwell, wu ming

            The polls are showing that the demographic which favors romney far more than the nation does thought Romney did a better job.

            In my left leaning household of 15 who watched the debate we came to a completely different conclusion. Romney looked like a nervous attack weasel to us.

            "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

            by biscobosco on Thu Oct 04, 2012 at 12:29:57 AM PDT

            [ Parent ]

            •  I came to a different conclusion too . . . (0+ / 0-)

              that was more in line with your experience as far as my personal reaction goes.

              However, I'm not going to say from my own perception of the debate is representative of the entire audience that watched the debate (or even a majority of viewers).

              Was the audience that watched the debate representative of the entire voting population?  No, it probably wasn't.  

              The CNN poll shows a GOP partisan advantage pre-debate, even though the national polls indicate a Dem advantage.  Romney's net favorables also skewed more positive than they do in national polls by a significant degree.  All of those factors point toward the idea that the viewing audience was more GOP leaning than the population as a whole.  This is almost certainly true.  If the viewing audience skews Republican, then perceptions of who the winner was are likely to skew in the same direction.

              •  if the sample is representative of the viewing (0+ / 0-)

                audience.

                It seems like if you are using 430 people to represent 56 million, you have a chance of being off a little.

                "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                by biscobosco on Thu Oct 04, 2012 at 01:58:55 AM PDT

                [ Parent ]

                •  oh and also (0+ / 0-)

                  There is also the chance that the selection was biased. (by that I don't mean to imply intentionally biased, only that there was selection bias for some other reason.)

                  "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                  by biscobosco on Thu Oct 04, 2012 at 02:00:06 AM PDT

                  [ Parent ]

              •  If you assume (0+ / 0-)

                That CNN's methods of selecting the sample truly produced a representative random sample.

                We don't know that this is true yet. It would be interesting to see the other polls which diverged considerably from this one, and also to see what the exact demographics of this poll were, and compare that against what Nielsen ratings say.

                "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                by biscobosco on Thu Oct 04, 2012 at 02:04:27 AM PDT

                [ Parent ]

    •  But (5+ / 0-)

      100% of debate watchers were not from the south, but the respondents to this poll are all from the south.

      •  Again, just so people aren't confused, (3+ / 0-)

        The reason the other regions say N/A in the columns of the internals is only because the margin of error for those subsets of the poll is too high to be meaningful.  And actually the South is now the most populous region of the country, although it does look like it was overpolled here.

        •  But (5+ / 0-)

          the entire under fifty crowd, as a block, is also outside the margin of error? Same withe the non-white block? I realize we have a lot of seniors in the country, but seriously?

          •  Only 430 people in this poll, as opposed to 1,000+ (5+ / 0-)

            in normal national polls, so the margin of error is high to begin with, and thus it makes even releasing internals mostly pointless.

            Although if they had polled an accurate number of non-white people, the margin of error would've been small enough to report the numbers.  It looks like they're only including internals of subsets with a MoE below 10%, which I believe is the common number among pollsters.

            •  Agreed. (2+ / 0-)
              Recommended by:
              typo ink, NotGeorgeWill

              "When fascism comes to America it will be wrapped in the flag and carrying a cross." - Sinclair Lewis

              by Bob Duck on Thu Oct 04, 2012 at 12:22:30 AM PDT

              [ Parent ]

            •  so then, (1+ / 0-)
              Recommended by:
              wu ming

              Less than 10% of their sample was in any age group under 50?
              Less than 10% of their sample was Hispanic?
              Less than 10% of their sample was from the West, Northeast, etc.?
              Seems hard to believe that this was random. There seems to be selection bias.

              "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

              by biscobosco on Thu Oct 04, 2012 at 12:59:03 AM PDT

              [ Parent ]

              •  You're misinterpreting margin of error (2+ / 0-)
                Recommended by:
                ItsSimpleSimon, tiredntexas

                The poll's overall sample size is 430 people, which has a margin of error of 4.7%.  As you poll fewer and fewer people, the sample size gets bigger and bigger.

                In this particular sample, any group that contains less than approximately 100 people, or 23% of the sample (I'm doing a reverse calculation here), will have a margin of error of 10%+.  

                So again, the poll has issues, but it's not as bad as it seems at first.

                •  huh how does the sample size get bigger (1+ / 0-)
                  Recommended by:
                  typo ink

                  as you poll fewer people?

                  Other than that, what you say makes sense and thanks for explaining. I thought it was 600, not 430.

                  In that case, it would indeed be interesting to see the true data, the actual demographics.

                  Also of interest is that although the US West is about as populous as the South? we know that less than 23% of the sample was from the West.  Which certainly means either that the sample was skewed, or the viewership was skewed.

                  But I suppose the main takeaways are that the poll is not large enough to have a very good MOE on any of the results, and secondly we don't know if it oversampled Romney voters, or whether in general more Romney voters watched the debates.

                  "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                  by biscobosco on Thu Oct 04, 2012 at 01:43:59 AM PDT

                  [ Parent ]

                  •  Ah, typo! Meant to say margin of error gets bigger (0+ / 0-)

                    Now you see how I get my name.

                    The South is the most populous region of the US.  That's why I didn't want to criticize that aspect of the poll too much.

                    Here's the regional breakdown of the electorate from the '08 exit poll:  Northeast 21%, Midwest 24%, South 32%, West 23%.

                    •  I think the west is now more populous than that (0+ / 0-)

                      But probably still only around 25%  or so..

                       the basic point you are making is that there would be no crosstabs for any demographic group which was less than 23% of the sample..

                      Since you know a fair amount about polling.. I'm wondering whether you think 430 people is a reasonable enough size sample.

                      (If the viewing audience was 56 million similar to last debates)

                      "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                      by biscobosco on Thu Oct 04, 2012 at 02:16:23 AM PDT

                      [ Parent ]

                      •  A sample size of 430 people creates a MoE of 4.7% (0+ / 0-)

                        which is pretty high, but acceptable.  But as we've discussed, it makes the crosstabs mostly useless.  I'm guessing CNN polled such a small sample so they could complete the snap poll and breathlessly announce the results as quickly as possible.

                        Normally pollsters use a sample size of at least 1,000 or so for a national poll.  You usually only see samples of 400-500 in state polls.

                        •  ok, so that MOE (2+ / 0-)
                          Recommended by:
                          wishingwell, tiredntexas

                          Makes any change in approval ratings essentially meaningless.
                          I still believe there was some kind of selection bias in this poll, but as mentioned elsewhere, Nielsen would tell us if that is true.  

                          Do you know if you need a subscription to get that data?

                          "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

                          by biscobosco on Thu Oct 04, 2012 at 02:34:49 AM PDT

                          [ Parent ]

                        •  note it was a subsample from a previous poll (0+ / 0-)

                          Offhand I would guess they attempted to reinterview everyone from that poll who was qualified and willing.

                          We should be grateful to them for that, since it gives us an interesting result: the candidate favorables hardly budged.

                          Election protection: there's an app for that!
                          Better Know Your Voting System with the Verifier!

                          by HudsonValleyMark on Thu Oct 04, 2012 at 03:47:18 AM PDT

                          [ Parent ]

        •  hard to buy that (2+ / 0-)
          Recommended by:
          wishingwell, elmo

          Geography is not random.  You can get a geographically diverse sample.  The area codes are very helpful that way.

        •  Exactly. (1+ / 0-)
          Recommended by:
          Bob Duck

          Well-said.

        •  South only represents about 1/3 of the population (1+ / 0-)
          Recommended by:
          wishingwell

          So if 50 million people watched, (about 6 million less than in 2008) and 90 % were over 50 and registered voters in the south, I suspect we are reaching a state of impossibility.  

          90% of 50 = 45 million  

          Lets say 110 million in the south, and charitably, 35% of those are over 50. Of course we have to leave out black people, lets say they are 20% of southerners.  
          so 110 - 20% = 110 - 22 = 88 million whites * 35% = approx 31 million white southerners over 50.

          So if 100% of  white southerners over 50 were watching the debate, it still would not be enough. They would be short  by 15 million.

          This is absurd.

          "We have always known that heedless self-interest was bad morals; we know now that it is bad economics" - F.D.R.

          by biscobosco on Thu Oct 04, 2012 at 12:37:45 AM PDT

          [ Parent ]

        •  w/430, N/A= so few, might as well be 0. (1+ / 0-)
          Recommended by:
          wishingwell

          Srsly, stop trying to defend this bad sample.  

          Does it mean BO won the debate. No.  But it also doesn't mean the narrative CNN is obviously trying to set against BO is true either.

          •  Actually, with only 430, a subgroup of 100 is N/A. (2+ / 0-)
            Recommended by:
            ItsSimpleSimon, tiredntexas

            That's my point.  With the overall sample size so small, a subgroup that constitutes 23% of the sample will show up as N/A.  So it's possible that the West, Northeast, and West all constituted about 22-23% of the poll, and that would actually be reasonably accurate.

            I agree that the sample is bad overall, and I'm not defending it.  I'm just trying to help people get it right so they don't attack the poll on an incorrect basis.  Attack the poll because it's too old or too white, but don't attack it because it "only included Southerners".

            •  Sure, but if 3/4s was southerners and they over-fa (0+ / 0-)

              vor Thug/1% by, say, 30% compared to all other sectors of the country, that would skew overall results 1%'s way by a (back of the envelope) relative 10% of so.  Add additional 1%/Thug bias from oversampling other friendly cohorts and much of the difference btwee this and the CBS poll disappears.

              Sure, that's not good, but its not the crushing blowout CNN is selling.

        •  Oh, come on (3+ / 0-)
          Recommended by:
          wishingwell, elmo, tiredntexas

          They sought out this demographic group.  It'd be OK (weird but OK) so long as they consistently labeled it as such, including in headlines.  They did not.

          Pro-Occupy Democratic Candidate for California State Senate, District 29 & Occupy OC Civic Liaison.

          "I love this goddamn country, and we're going to take it back." -- Saul Alinsky

          by Seneca Doane on Thu Oct 04, 2012 at 03:12:15 AM PDT

          [ Parent ]

Subscribe or Donate to support Daily Kos.

Click here for the mobile view of the site