cBS poll the left is trying to tout

[dullard]

Originally posted by: ShadesOfGrey
Moral: clearly you do not understand weighing, nor the point of this thread as noted in the OP

I do understand weighting. From what you just wrote, it is clear that you don't understand it. After weighting, that poll was the same as all other polls. Thus the weighting was done PROPERLY.

 

[ShadesOfGrey]

Originally posted by: Bowfinger

Originally posted by: ShadesOfGrey

Originally posted by: dullard
Poll using 36% republicans and 38% democrats. Exact same result as the CBS poll (within margin of error). Moral: adjusting numbers (when done properly) does not affect the results.

Moral: clearly you do not understand weighing, nor the point of this thread as noted in the OP

Never, ever, ever ... about anything, no matter how much evidence we provide. You haven't changed a bit.

Get well soon.

You obviously can't read. The numbers are right there for you to read yet you claim you've provided evidence against them suggesting they are good. Well, clearly they are not good because the Republican sample was too low to begin with and was lowered even more by weighing. They should have used political affiliation weighing like more respectable political pollsters do.

I guess you think Zogby is wrong since he uses political affiliation in his weighing.

But that's right, Bowfinger and his little gaggle of leftist are never wrong. Never- ever. Because according to them, the other side is always wrong. :laugh:

 

[ShadesOfGrey]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
Moral: clearly you do not understand weighing, nor the point of this thread as noted in the OP

I do understand weighting. From what you just wrote, it is clear that you don't understand it. After weighting, that poll was the same as all other polls. Thus the weighting was done PROPERLY.

Heh, so you think Zogby doesn't understand it too? :laugh:

 

[dullard]

Originally posted by: ShadesOfGrey
Heh, so you think Zogby doesn't understand it too? :laugh:

I don't watch Zogby and I didn't read the whole thread. What is your beef with Zogby's weighTings?

 

[Bowfinger]

Originally posted by: ShadesOfGrey

Originally posted by: Bowfinger

Originally posted by: ShadesOfGrey

Originally posted by: dullard
Poll using 36% republicans and 38% democrats. Exact same result as the CBS poll (within margin of error). Moral: adjusting numbers (when done properly) does not affect the results.

Moral: clearly you do not understand weighing, nor the point of this thread as noted in the OP

Never, ever, ever ... about anything, no matter how much evidence we provide. You haven't changed a bit.

Get well soon.

You obviously can't read. The numbers are right there for you to read yet you claim you've provided evidence against them suggesting they are good. Well, clearly they are not good because the Republican sample was too low to begin with and was lowered even more by weighing. They should have used political affiliation weighing like more respectable political pollsters do.

I guess you think Zogby is wrong since he uses political affiliation in his weighing.

But that's right, Bowfinger and his little gaggle of leftist are never wrong. Never- ever. Because according to them, the other side is always wrong. :laugh:

Yes dear. You've expressed your (unqualified) opinion on this a dozen times. Repeating it a dozen more still won't make it truth. Your partisan allegations deny the science of statistical sampling. Several people produced evidence demonstrating your ignorance on the matter. Now Dullard has produced further, empirical evidence your claim is baseless. I know how much you hate to be wrong, but the facts speak for themselves, loud and clear. Deal with it.

 

[ShadesOfGrey]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
Heh, so you think Zogby doesn't understand it too? :laugh:

I don't watch Zogby and I didn't read the whole thread. What is your beef with Zogby's weighTings?

Clue

 

[Bowfinger]

Originally posted by: smack Down
What is up with not capitilizing the 'c' in CBS? You keep claiming the sample is bad but with no proof. The fact that the poll results match other poll is not irrelivent it implies very strongly that the sample is correct and your just a hack.

He first started doing that when the "scandal" broke about Dan Rather's story on Bush's Guard service. He thinks he's clever.

 

[dullard]

Originally posted by: ShadesOfGrey
Clue

Need more clues. What about Zogby's weightings don't you like?

 

[ShadesOfGrey]

Originally posted by: Bowfinger

Originally posted by: ShadesOfGrey

Originally posted by: Bowfinger

Originally posted by: ShadesOfGrey

Originally posted by: dullard
Poll using 36% republicans and 38% democrats. Exact same result as the CBS poll (within margin of error). Moral: adjusting numbers (when done properly) does not affect the results.

Moral: clearly you do not understand weighing, nor the point of this thread as noted in the OP

Never, ever, ever ... about anything, no matter how much evidence we provide. You haven't changed a bit.

Get well soon.

You obviously can't read. The numbers are right there for you to read yet you claim you've provided evidence against them suggesting they are good. Well, clearly they are not good because the Republican sample was too low to begin with and was lowered even more by weighing. They should have used political affiliation weighing like more respectable political pollsters do.

I guess you think Zogby is wrong since he uses political affiliation in his weighing.

But that's right, Bowfinger and his little gaggle of leftist are never wrong. Never- ever. Because according to them, the other side is always wrong. :laugh:

Yes dear. You've expressed your (unqualified) opinion on this a dozen times. Repeating it a dozen more still won't make it truth. Your partisan allegations deny the science of statistical sampling. Several people produced evidence demonstrating your ignorance on the matter. Now Dullard has produced further, empirical evidence your claim is baseless. I know how much you hate to be wrong, but the facts speak for themselves, loud and clear. Deal with it.

Clue for you too It's not my unqualified opinion anyway. Anyone can see that the sample was bad if they tried removing their partisan blinders. Unfortunately that is something you've shown you can't do.

I'm sorry Dullar, you, and your gaggle can't seem to deal with the fact that the sample was bad, but the numbers, facts, and experts(Zogby) speak for themselves. Deal with it.

 

[dullard]

Originally posted by: ShadesOfGrey
I'm sorry Dullar, you, and your gaggle can't seem to deal with the fact that the sample was bad, but the numbers, facts, and experts(Zogby) speak for themselves. Deal with it.

What was bad about the numbers? The poll results were the exact same. That means the weighting numbers were CORRECT for that CBS poll. Deal with it.

 

[ShadesOfGrey]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
Clue

Need more clues. What about Zogby's weightings don't you like?

I like his. Unfortunately cBS doesn't use similar so they get resulting bad samples like I started this thread about.

 

[dullard]

Originally posted by: ShadesOfGrey
I like his. Unfortunately cBS doesn't use similar so they get resulting bad samples like I started this thread about.

All polls have bad samples. Thus the polls are weighted to reduce that effect. The CBS weightings ended up having the same result as other polls' weightings. Thus the weightings are correct.

 

[Bowfinger]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
Clue

Need more clues. What about Zogby's weightings don't you like?

Zogby includes political party affiliation in the factors it uses to weight its polls when analyzing elections. Sir SkG therefore clings to this as proof that all polls with any political implications MUST also use party weighting. It is the only piece of evidence he can twist to seem to support his position, so he wields it like a club to attack the overwhelming evidence against him. He refuse to acknowledge there's a difference between pure election polls and more general public opinion polls.

 

[ShadesOfGrey]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
I'm sorry Dullar, you, and your gaggle can't seem to deal with the fact that the sample was bad, but the numbers, facts, and experts(Zogby) speak for themselves. Deal with it.

What was bad about the numbers? The poll results were the exact same. That means the weighting numbers were CORRECT for that CBS poll. Deal with it.

No, it doesn't. You obviously haven't looked at the numbers. Do you think a 24% sample of Republicans is correct vs a 35% Democrat?

I've posted then percentages Zogby uses for his political polls.

 

[ShadesOfGrey]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
I like his. Unfortunately cBS doesn't use similar so they get resulting bad samples like I started this thread about.

All polls have bad samples. Thus the polls are weighted to reduce that effect. The CBS weightings ended up having the same result as other polls' weightings. Thus the weightings are correct.

No, they didn't factor in political affiliation when taking a POLITICAL POLL. What part of that do you and Bowfinger not understand? When taking a POLITICAL POLL your sample should reflect political demographics that represent what you are trying to say it represents. In this case, the USA. Do you think 24% vs 35% is correct? Zogby doesn't.

 

[Bowfinger]

Now that Sir What's-his-name's bias claims have been thoroughly discredited, both scientifically and empirically, is anyone is interested in discussing the first poll's findings?

Interesting poll. Thanks for the link to the .pdf. Several other interesting results. For example:

• 51% say the Plame leak is of "Great importance" to America, only 12% see it as of "little or no importance". This compares to 37% who thought the Clinton-Lewinsky story was of little/no importance, and 45% who thought Whitewater was of little/no importance.
  
• 64% of America thinks BushCo was deceptive about Iraq's WMDs before the invasion, either due to "Mostly lying" or to "Hiding important elements".
  
• While Bush's "favorable" rating has tanked to 33%, Cheney's is an even more abysmal 19%.
  
• Only 31% of Americans think invading Iraq was worth its costs. 42% still think it was the right thing to do, however, giving a confused 11% who think it was right to invade yet not worth the cost. Different strokes, I guess.
  
• Just less than half of Americans think Iraq will ever become a stable democracy; the overwhelming majority think it will take over two years.
  
• 50% of Americans think our trrops should leave "as soon as possible"; only 43% agree with Bush that they should stay as long as it takes.

Doesn't look like GW and John Q. Public see eye to eye on major issues. Pity more of them weren't paying attention a year ago.

 

[dullard]

Originally posted by: ShadesOfGrey
No, it doesn't. You obviously haven't looked at the numbers. Do you think a 24% sample of Republicans is correct vs a 35% Democrat?

I've posted then percentages Zogby uses for his political polls.

But those 24% numbers are meaningless. In this particular poll, it had to be adjusted to 24% to be the most accurate due to biases. In other polls, in other times, that number will vary. It does not have to match the percent of people who are republican, it doesn't have to match the percent of people who vote republican. All it has to do is to reduce the bias in this particular poll on this particular date as much as possible.

 

[ExpertNovice]

Originally posted by: EatSpam
So his approval ratings are 35% or 40%... still piss poor. You'd think with the way you guys worship Bush, his approval ratings could at least exceed 50%.

Of course. He has given much too much control to the liberals in congress, he is (as we warned by Mr. Forbes) much too liberal for conservatives, he is not the fascist or communist hero the liberals want, but even worse the media refuses to allow him to present his position. Even when they have been demanding to hear it.

Say it loud enough and long enough and it will become truth. As usual, the Fascists support the mainstream media hype.

Plus, he is much too liberal. Could another Reagan ever be elected with the mainstream media so much in control of the liberal minds?

 

[dullard]

We can just run the numbers of course.

Unweighted CBS poll: Approval = 36% +- (3%+x%)
Weighted CBS poll: Approval = 35% +- (3%+x%)

Where x is the unknown and unmeasurable poll question bias. Lets just assume x=1. The 3% is the insufficient number of people polled margin of error.

Or in another format:
Unweighted approval is 90% likely to be between 32% and 40%
Weighted approval is 90% likely to be between 31% and 39%.

The "fabricated" numbers are basically the same as the unweighted numbers. If, for an example, we had omnipotent power to know the true approval is 38%, then we can see that both the weighted and unweighted gave that same answer.

 

[ShadesOfGrey]

Originally posted by: Bowfinger
Now that Sir What's-his-name's bias claims have been thoroughly discredited, both scientifically and empirically, is anyone is interested in discussing the first poll's findings?

Not only are your claims false, this thread isn't about the results. Try reading the OP as I've suggested numerous times.

 

[ShadesOfGrey]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
No, it doesn't. You obviously haven't looked at the numbers. Do you think a 24% sample of Republicans is correct vs a 35% Democrat?

I've posted then percentages Zogby uses for his political polls.

But those 24% numbers are meaningless. In this particular poll, it had to be adjusted to 24% to be the most accurate due to biases. In other polls, in other times, that number will vary. It does not have to match the percent of people who are republican, it doesn't have to match the percent of people who vote republican. All it has to do is to reduce the bias in this particular poll on this particular date as much as possible.

No they aren't meaningless. This poll was about politics. When polling people about politics and political issues your sample should reflect the political breakdown of the country(or area you are polling). Otherwise, why not just ask a bunch of Democrats? The rest of the Demographics might be fine if you did so but if you were trying to present the data as representative of anything but what Democrats think, you are misrepresenting things.
Again, the results are irrelevant to the discussion of the sample. You derive results from the sample, not prove sample by results. If cBS would have adjusted their sample for political affiliation, this thread wouldn't exist even if the results were the same. This has always been about the bad sample done by cBS.

 

[Czar]

from this http://www.zogby.com/about/faq.cfm#question7

I read a lot of polls and yours is so different from the others - what makes your answers so different (and accurate)?

JZ: "We poll only likely voters who are different from just all adults. In addition, we poll all day long - 9am to 9pm local time (to the region we're calling). Finally, we apply weighting for party identification to ensure that there is no built-in Democratic bias in our sampling."

why do they talk about a built in democratic bias?

 

[ShadesOfGrey]

Originally posted by: Czar
from this http://www.zogby.com/about/faq.cfm#question7

I read a lot of polls and yours is so different from the others - what makes your answers so different (and accurate)?

JZ: "We poll only likely voters who are different from just all adults. In addition, we poll all day long - 9am to 9pm local time (to the region we're calling). Finally, we apply weighting for party identification to ensure that there is no built-in Democratic bias in our sampling."

why do they talk about a built in democratic bias?

Because Zogby is an admitted Democrat.

 

[totalcommand]

Originally posted by: dullard

Originally posted by: ShadesOfGrey
No, it doesn't. You obviously haven't looked at the numbers. Do you think a 24% sample of Republicans is correct vs a 35% Democrat?

I've posted then percentages Zogby uses for his political polls.

But those 24% numbers are meaningless. In this particular poll, it had to be adjusted to 24% to be the most accurate due to biases. In other polls, in other times, that number will vary. It does not have to match the percent of people who are republican, it doesn't have to match the percent of people who vote republican. All it has to do is to reduce the bias in this particular poll on this particular date as much as possible.

Which is why a FoxNews poll gave similar numbers, even with largely different political identification ShadesOfGray

 

[dullard]

Originally posted by: ShadesOfGrey
This poll was about politics. When polling people about politics and political issues your sample should reflect the political breakdown of the country(or area you are polling). Otherwise, why not just ask a bunch of Democrats? The rest of the Demographics might be fine if you did so but if you were trying to present the data as representative of anything but what Democrats think, you are misrepresenting things.

Why use just a poll of likely voters (such as Zogby)? If you apply a poll of likely voters to the American public, you are misrepresenting things. Not all Americans vote. Many non-voters care about public policies.

Again, the results are irrelevant to the discussion of the sample. You derive results from the sample, not prove sample by results. If cBS would have adjusted their sample for political affiliation, this thread wouldn't exist even if the results were the same. This has always been about the bad sample done by cBS.

The results ARE relevant. If after adjusting you get the correct results, then your weighting was correct. If after adjusting you get incorrect results, then your weighting was incorrect. You cannot judge a poll's merrits without using the results.