Free Republic
Browse · Search
Bloggers & Personal
Topics · Post Article

Skip to comments.

One Obvious Reason the Polls are Biased
Stolen Thunder Blog ^ | October 15, 2008 | DJ Drummond

Posted on 10/15/2008 11:20:58 AM PDT by St. Louis Conservative

I have said and will say again, that the opinion polls this year are simply wrong. They have fiddled with weighting and wording and various pieces of the demographics to create a false impression. You can either believe them or not, but as I have shown in the numbers for weeks now, believing the polls would be naïve at the very least.

But if the polls have been so biased, one may reasonably ask why that is so. I myself have commended groups like Gallup for a very professional job over many years, and even though I strongly disagree with the conclusions published by groups like CBS News, I applaud their open way of reporting at least some of the significant internal data. In fact, it is CBS News which reveals how this bias is operating, and how even well-intentioned pollsters can make major blunders in their assumptions.

I disagree with CBS News because of how it weights its respondent pool. And lately, what I have seen is a trend, verging on the ridiculous, of far too many Democrats in the pool to make any sense at all. This has been happening in both national polls and in state polls. For national polls, I mentioned some weeks back how Gallup managed to show Obama declining or staying steady in every political affiliation group over a week while McCain was steady or gained in every such group, yet Gallup’s headline claimed Obama was gaining support overall, a mathematical impossibility without manipulating the proportionate weights.

(Excerpt) Read more at stolenthunder.blogspot.com ...


TOPICS: Miscellaneous; Politics; Society
KEYWORDS: polls
I don't necessarily agree. I think the partisan weighting of these polls *probably* reflects reality, although the actual turnout model remains to be seen. Please drop in with your thoughts.
1 posted on 10/15/2008 11:20:58 AM PDT by St. Louis Conservative
[ Post Reply | Private Reply | View Replies]

To: St. Louis Conservative

The pollsters are employed mainly by the media. It is in the media’s best interest to keep excitement in the Presidential race going to the very end, to maximize the advertising dollars both campaigns are spending.

It’s not about taking the public pulse, anymore, it’s about enriching the media’s purse.


2 posted on 10/15/2008 11:24:58 AM PDT by JennysCool (There are three kinds of lies: lies, damn lies, and the polls.)
[ Post Reply | Private Reply | To 1 | View Replies]

To: St. Louis Conservative

Neither in 2006 nor in 2004 we had a +10% (min) Democrat national voter turnout compared to Republicans. Also in state polls, i.e. Virginia weighting 7-10% more Dem is ridiculous. Voter turnout for Republicans will be extremely high this time, because of Palin rallying the base and the anti-Obama vote.


3 posted on 10/15/2008 11:25:52 AM PDT by SolidWood
[ Post Reply | Private Reply | To 1 | View Replies]

To: St. Louis Conservative

A pollster would get a friendly “go away” from me.


4 posted on 10/15/2008 11:26:09 AM PDT by MarineBrat (My wife and I took an AIDS vaccination that the Church offers.)
[ Post Reply | Private Reply | To 1 | View Replies]

To: St. Louis Conservative

But but but I thought all these polls were accurate, and John McCain was down 14% and had no hope?

/


5 posted on 10/15/2008 11:46:53 AM PDT by Titus Quinctius Cincinnatus (Here they come boys! As thick as grass, and as black as thunder!)
[ Post Reply | Private Reply | To 1 | View Replies]

To: St. Louis Conservative

Polling is mostly via telephonic means.

Time of day is important.

Hangups are important, as are all other nonrespondents.

Usually a poll will look at the proportions of dems and repubs and indies registered in a state and then gather data from registered voter lists until a fixed proportion of each is obtained on a fixed sample of RESPONDENTS.

If an analysis of nonrespondents is included, then it becomes more clear whether a selection bias exists. So for example if there are twice as many nonrespondents among repubs as there are dems, it infers that repubs are working. If the percentage of indies that do not respond is far less, then it tells you indies are home and possibly not working. People are not working listen to the news which is usually biased to dems. They will say that they think Obama will win because the television says so. Also people sitting at home may be out of work and upset in general so they default to Obama.

In order to get a better breakdown, the pollster has to separate informed voters from uninformed voters. Other info is important such as whether the voter voted last election and for who. Turnout is the key predictor of a poll.

Turnout is so important that the dems have earmarked hundreds of millions of dollars of taxpayer money to ACORN. This is what makes ACORN so dangerous.

I think if taxpayer money is going to be used we should get money for scrubbing down the voter rolls because elections offices don’t seem to do it as well as they should. Yet any citizen can access voter roll data and start checking for duplicates, for dead voters, for voters registered in other states and so forth.

I think the RNC should be sending each member a list of voters to check over and challenge sheets with pre-paid FEDEX envelopes to be sent to respective election offices to investigate and invalidate those challenged on the rolls. For example why are there 30,000 or more convicted felons registered to vote in Florida? Who is challenging their registrations?

And I think the RNC should pay $5 for each successful challenge.


6 posted on 10/15/2008 11:47:23 AM PDT by Hostage
[ Post Reply | Private Reply | To 1 | View Replies]

To: St. Louis Conservative

There is an exceptional amount of abuse going on in polling this year.

I am surprised to see even Rasmussen getting into the game with his 5-6% preference for Democrats.

I infer that the best justifications for this are the high dem turnouts in the primaries leading pollsters to say they are reflecting voter participation rates for the spring. I think there are several important rebuttals to his view that should be considered by pollsters and conservatives who are too ready to wet their pants on this one:

1. Operation chaos transferred voters from the Republican and indpendent base into the democratic base. The purpose was to confuse the democrats and insure their eventual defeat in the general election. Pollsters are not clueless about this and ought to be willing to forego the conclusion that these people really have changed sides.

2. Even if Obama has increased registrations— which is not clear especially with the bizarre acorn activities— Democrats more than ever have an incentive to bolt from Obama. Gallup’s most recent Oct 5 breakdowns even suggest that more dems are breaking for McCain than vice versa. Obamabots have violated the civil rights of Hillary Clinton supporters in multiple states. The conduct was egregious, outrageous and most importantly unforgettable. It is easy to envision where 20-35% of the democratic base will either refuse to vote or vote for McCain.

3. There is zero empirical evidence to support the new innovative models for participation being used by Gallup, Rasmussen and others. Gallup projects near 70% voter turnout in the current election. That is absurd. Crossing 50% turnout is a big deal. To believe that we will have 70% turnout is to be actively involved in the false hype of the Obama campaign. This gives license to voter fraud and lays the ground work for uncivil actions after the election results.

I really hope that conservatives are not falling for this pscyhological warfare being conducted by the media and other epistemological entities. This is raw deception and should be both ignored and resisted.


7 posted on 10/15/2008 11:49:37 AM PDT by lonestar67 (Its time to withdraw from the War on Bush-- your side is hopelessly lost in a quagmire.)
[ Post Reply | Private Reply | To 1 | View Replies]

To: St. Louis Conservative
My caller-ID records incoming calls.

I've had several calls during the day that appear to have been from pollsters.

THEY DON'T CALL AT NIGHT.

Hmmmmm ....

8 posted on 10/15/2008 11:49:53 AM PDT by ArrogantBustard (Western Civilization is Aborting, Buggering, and Contracepting itself out of existence.)
[ Post Reply | Private Reply | To 1 | View Replies]

To: St. Louis Conservative

Maybe the polls can be neutralized? How? Well, since the bias is toward Dems, especially for Senator Obama, lets play along. When a pollster calls, pretend you’re a Dem and go along with all the Obama positions. Pretty soon, they’ll start seeing 60% or even 70% for Obama. Obviously, incorrect, but they’ll have no way to correct them, no way to show the real picture. Suddenly, they really will be useless results. Same is true for exit polls, landslide for Obama, yeah right.


9 posted on 10/15/2008 12:00:19 PM PDT by papersonusa
[ Post Reply | Private Reply | To 1 | View Replies]

To: lonestar67
Your analysis is interesting, especially regarding Operation Chaos. Also, The One is unloading money into ads like mad and bought 30-minute slots as well. Is a pre-won campaign going to do that unless is it necessary? By the by, the latest Gallup of likelies shows The One up by 3% over McCain. Hmph.
10 posted on 10/15/2008 12:26:39 PM PDT by TheGeezer
[ Post Reply | Private Reply | To 7 | View Replies]

To: ArrogantBustard
My caller-ID records incoming calls.

I've had several calls during the day that appear to have been from pollsters.

THEY DON'T CALL AT NIGHT. Hmmmmm ....

Same with my home.

I have had at least five calls with the word "poll" in the name and all calls were during the early afternoon.

11 posted on 10/15/2008 12:31:28 PM PDT by OldMissileer (Atlas, Titan, Minuteman, PK. Winners of the Cold War)
[ Post Reply | Private Reply | To 8 | View Replies]

To: lonestar67

It is funny Operation Chaos is conducted right out in the open yet Liberals and the MSM can’t see it. You know the old saying “You can’t fool all of the people all of the time, unless they are liberals.”


12 posted on 10/15/2008 12:45:24 PM PDT by YdontUleaveLibs (Reason is out to lunch. How may I help you?)
[ Post Reply | Private Reply | To 7 | View Replies]

To: St. Louis Conservative

Maybe. But the if the weighting is made possible on the back of registration increases - increases made possible by A.C.O.R.N. registering phantoms and pets, then the may be improperly weighted.


13 posted on 10/15/2008 1:03:42 PM PDT by Sgt_Schultze
[ Post Reply | Private Reply | To 1 | View Replies]

To: YdontUleaveLibs

The liberal community believes they are profound and intrinsically superior to conservatives to a point of calling for violence against Palin and other conservative leaders.

That profound bias easily filters out contrary information.


14 posted on 10/15/2008 1:11:27 PM PDT by lonestar67 (Its time to withdraw from the War on Bush-- your side is hopelessly lost in a quagmire.)
[ Post Reply | Private Reply | To 12 | View Replies]

To: ArrogantBustard
THEY DON'T CALL AT NIGHT.

Hard working Repubs are ... at work. Duh. Their [homeschooling] wives have programmed the answering machine to screen calls. If it sounds like a marketer or pollster, she does not pick up. If she's expecting a call and does pick only to hear "dead air", she's smart enough to know that she's got 5 seconds to hang up before she has to brush off some marketer or pollster.

So, I'm not surprised that Repub/Conservative input is under-represented in these polls. Vote on Nov 4th and surprise the hell out of these insufferable socialists. Let's give 'em another 1994 shock.

15 posted on 10/15/2008 2:33:26 PM PDT by nonsporting
[ Post Reply | Private Reply | To 8 | View Replies]

Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.

Free Republic
Browse · Search
Bloggers & Personal
Topics · Post Article

FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson