cBS poll the left is trying to tout

[sandorski]

This is like watching a tennis match.

 

[smack Down]

Originally posted by: ShadesOfGrey

Originally posted by: smack Down

Originally posted by: ShadesOfGrey

Originally posted by: homercles337

Originally posted by: ShadesOfGrey
Just because you claim the results are similar does not change the fact that the sample is bad.

You have yet to provide evidence of ANYTHING you claim! Youre just as bad as Zendari or Pabster, in fact given your tactics i bet you are one of them. Mods can check IPs, but i cant. Either put up or STFU! Do you have proof of a sampling bias and subsequent biased weights, which willl bias stats even further against your agenda? If not, STFU!

Hello, it's all in the OP. The sample of Republicans was 28% which is lower than the average. Then due to their other weighing, the result was a 24% sample of Republicans. THAT is a bad sample because it under samples Republicans. Can you not read? The numbers are right there in plain sight.

So no matter how many times you try to claim there is no evidence, it doesn't change the fact that I have presented it. It also doesn't change the fact that you and others continue to refuse to accept them. No wonder you people on the left can't win - you don't listen and you refuse to accept reality when it is presented to you.

Where not the one saying a poll is wrong because it doesn't fell like. All you have shown is the results of the poll which CBS has on there webpage that is hardly evidence that CBS is faking the poll.

It's obvious you haven't even read the OP. So just like homercles337 before you: "you obviously aren't willing to even read so you are a waste of time. Maybe if you read the thread and have a specific question that I haven't already answered, I might just respond to you again but if not, then consider me done with your continuous ignornace."

Show one of the following and some one besides your right wind circle jerk partners might respect you.

That the poll is an out lier compared to other polls

That at the time the poll was taken the party distrubution is different then the one given

Or, a flaw in there method that results in a low number of republician responders.

 

[shira]

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

 

[ShadesOfGrey]

Originally posted by: shira

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

Exactly. That's why since they weighted their samples for some demographics, they should have done it for political affiliation since it was a poll on politics.

Nothing you posted refutes anything I've stated nor does it make the cBS any less bad.

I fully understand this issue, you like the others seem to be willingly ignorant about what I've stated.

 

[sandorski]

Originally posted by: ShadesOfGrey

Originally posted by: shira

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

Exactly. That's why since they weighted their samples for some demographics, they should have done it for political affiliation since it was a poll on politics.

Nothing you posted refutes anything I've stated nor does it make the cBS any less bad.

I fully understand this issue, you like the others seem to be willingly ignorant about what I've stated.

It refutes everything you've stated. You may not see it, but it does.

 

[totalcommand]

Originally posted by: sandorski

Originally posted by: ShadesOfGrey

Originally posted by: shira

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

Exactly. That's why since they weighted their samples for some demographics, they should have done it for political affiliation since it was a poll on politics.

Nothing you posted refutes anything I've stated nor does it make the cBS any less bad.

I fully understand this issue, you like the others seem to be willingly ignorant about what I've stated.

It refutes everything you've stated. You may not see it, but it does.

I second that motion.

He directly refuted the stuff you keep repeating.

 

[Tab]

Originally posted by: totalcommand

Originally posted by: sandorski

Originally posted by: ShadesOfGrey

Originally posted by: shira

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

Exactly. That's why since they weighted their samples for some demographics, they should have done it for political affiliation since it was a poll on politics.

Nothing you posted refutes anything I've stated nor does it make the cBS any less bad.

I fully understand this issue, you like the others seem to be willingly ignorant about what I've stated.

It refutes everything you've stated. You may not see it, but it does.

I second that motion.

He directly refuted the stuff you keep repeating.

Seconded, my political science books echo the same.

You don't choose who you poll, it's not accurrate to go out and find 50 repubs and 50 dems.

 

[Czar]

Originally posted by: sandorski
This is like watching a tennis match.

rofl

 

[Czar]

Originally posted by: Tab

Originally posted by: totalcommand

Originally posted by: sandorski

Originally posted by: ShadesOfGrey

Originally posted by: shira

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

Exactly. That's why since they weighted their samples for some demographics, they should have done it for political affiliation since it was a poll on politics.

Nothing you posted refutes anything I've stated nor does it make the cBS any less bad.

I fully understand this issue, you like the others seem to be willingly ignorant about what I've stated.

It refutes everything you've stated. You may not see it, but it does.

I second that motion.

He directly refuted the stuff you keep repeating.

Seconded, my political science books echo the same.

You don't choose who you poll, it's not accurrate to go out and find 50 repubs and 50 dems.

Same here, the whole point people have been making since the begining.

 

[speedstream5621]

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%.

I don't know of any Republican who worships Bush. In fact, he is really not a Republican at all. As far as poll numbes are concerned, people feed off of energy, negative or positive. Poll numbers that have been fabricated or resulted from misleading questions (I think we can assume this wasn't the first time) provide negative energy to feed off of-and there are a lot of dumb people in the world who are not willing to take the time to educate themselves.

 

[Pabster]

Originally posted by: speedstream5621
As far as poll numbers are concerned, people feed off of energy, negative or positive. Poll numbers that have been fabricated or resulted from misleading questions (I think we can assume this wasn't the first time) provide negative energy to feed off of-and there are a lot of dumb people in the world who are not willing to take the time to educate themselves.

:thumbsup: QFT.

 

[Bowfinger]

Originally posted by: Czar

Originally posted by: Tab

Originally posted by: totalcommand

Originally posted by: sandorski

Originally posted by: ShadesOfGrey

Originally posted by: shira

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

Exactly. That's why since they weighted their samples for some demographics, they should have done it for political affiliation since it was a poll on politics.

Nothing you posted refutes anything I've stated nor does it make the cBS any less bad.

I fully understand this issue, you like the others seem to be willingly ignorant about what I've stated.

It refutes everything you've stated. You may not see it, but it does.

I second that motion.

He directly refuted the stuff you keep repeating.

Seconded, my political science books echo the same.

You don't choose who you poll, it's not accurrate to go out and find 50 repubs and 50 dems.

Same here, the whole point people have been making since the begining.

Agreed. Shira did an excellent job, soundly refuting SoG's partisan allegations.


Now that that's done, anyone want to talk about some of the poll's other findings?

 

[ShadesOfGrey]

Originally posted by: Bowfinger

Originally posted by: Czar

Originally posted by: Tab

Originally posted by: totalcommand

Originally posted by: sandorski

Originally posted by: ShadesOfGrey

Originally posted by: shira

Originally posted by: ShadesOfGrey

Originally posted by: shira
The main objective of this and most other polls is to assess the OVERALL level of approval/disapproval of the President. Understanding the component percentages is a secondary objective. The two objectives are at odds, unless you use a VERY large sample.

Note that even had CBS polled 39% Dems, 35% Repubs, and 26% Indies, the component results (for example, that 77% of Republicans approve of Bush) might well have been LESS accurate that the ones we're seeing here, since within "Republicans" there's also a complex demographic mix. And unless the "mix" at all levels is close to the actual percentages in the general poplulation, the results obtained will be skewed. So pollsters have to carefully weight their samples to achieve the best possible numbers from a sample group that unavoidably is NOT fully representive of the general population.

Suppose, for example, that there were 350 Republicans (about 35%) in the group originally chosen. But suppose that 40% of that 350 was evangelical Christians, whereas the actual percentage Republicans that are evangelicals is 30% (I'm making these numbers up, but the point remains the same). If one wished to get a more accurate idea of what Republicans believe about Bush, then one would want to randomly reduce the number of evangelicals in the Republican group by 35. That would help to get a more accurate result for Republicans, and also might help the accuracy of the overall result. But note that a consequence of this reduction is that the percentage of Republicans in the poll would be below 35%.

The point is, the objective of any poll is to obtain meaningful results, not to blindly choose a percentage of this polical group and a percentage of that, and assume that the results (absent weighting) will be acccurate.

Wrong wrong wrong again.

The main objective is overall level of the President, so don't you think they'd try to make their sample look like most of America?(yes) In this case while they adjusted thier sample to look like America using "normal" demographics, they neglected to add in the political weighing.

No, it wouldn't have been less accurate because they still would have adjusted for the other demographics.
Also it's funny that you want to claim that Republicans have a complex demographic mix, as if "Independents" or democrats don't :roll:

And you continue to prove my point. The existing sample is too heavy on democrats and Independents vs Republicans. Don't you think that just might have an affect on the poll? You want to claim a demographic within the Republican part might skew it, but undersampling them to begin with definately skews the data.

No one is blindly choosing a percentage. You obviously have zero clue what you are talking about. All the demographic stats have some sort of survey and data behind them, and that includes political affiliation.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

Exactly. That's why since they weighted their samples for some demographics, they should have done it for political affiliation since it was a poll on politics.

Nothing you posted refutes anything I've stated nor does it make the cBS any less bad.

I fully understand this issue, you like the others seem to be willingly ignorant about what I've stated.

It refutes everything you've stated. You may not see it, but it does.

I second that motion.

He directly refuted the stuff you keep repeating.

Seconded, my political science books echo the same.

You don't choose who you poll, it's not accurrate to go out and find 50 repubs and 50 dems.

Same here, the whole point people have been making since the begining.

Agreed. Shira did an excellent job, soundly refuting SoG's partisan allegations.


Now that that's done, anyone want to talk about some of the poll's other findings?

Actually no one has refuted anything. No one has shown how a 24% sample of Republicans is a good sample. It is not. It does not come close to the reality of today. Even Zogby, arguably the most accurate pollster uses party affiliation weighing and I've pointed to the percentages he uses.

So I guess you 5 clowns know better than Zogby about political polling, right? :roll:

BTW Bowfinger, this thread is not about the poll's findings no matter how much you want to divert this thread towards that. Now quit trolling.

sandorski - it refutes nothing. You obviously don't know how weighing adjusts your sample. Adding another component isn't difficult, it just makes the weighing process more complicated since you added another dimension to adjust for.

 

[Czar]

ShadesOfGrey,
They did not use a 24% sample of republicans, is that so hard to understand?

 

[ShadesOfGrey]

Originally posted by: Czar
ShadesOfGrey,
They did not use a 24% sample of republicans, is that so hard to understand?

They used a 28% sample which was reduced to 24 when they weighted the POLITICAL poll for demographic other than political affiliation.

Figure it out yet? :roll:

 

[Czar]

Originally posted by: ShadesOfGrey

Originally posted by: Czar
ShadesOfGrey,
They did not use a 24% sample of republicans, is that so hard to understand?

They used a 28% sample which was reduced to 24 when they weighted the POLITICAL poll for demographic other than political affiliation.

Figure it out yet? :roll:

No they did not, please understand

They used a sample based on the census data, then asked the questions to those who answered, one regarding their political affiliation or support. After the first phase was done they saw that the respondance sample did not reprisent an accurate relations to the census. So they added new samples based on the same criteria as before, age, sex, and so on. They asked those from the additional sample the same questions, including political affiliation or support which then reduced the total support for the republicans.

Get it now?

 

[ShadesOfGrey]

Originally posted by: Czar

Originally posted by: ShadesOfGrey

Originally posted by: Czar
ShadesOfGrey,
They did not use a 24% sample of republicans, is that so hard to understand?

They used a 28% sample which was reduced to 24 when they weighted the POLITICAL poll for demographic other than political affiliation.

Figure it out yet? :roll:

No they did not, please understand

They used a sample based on the census data, then asked the questions to those who answered, one regarding their political affiliation or support. After the first phase was done they saw that the respondance sample did not reprisent an accurate relations to the census. So they added new samples based on the same criteria as before, age, sex, and so on. They asked those from the additional sample the same questions, including political affiliation or support which then reduced the total support for the republicans.

Get it now?

Hello!?

Unweighted Total Respondents: 936
Republicans = 259 (27.67%)
Democrats = 326 (34.83%)
Independents = 351 (37.5%)

Weighted Total Respondents: 937
Republicans: 223 (23.80%)
Democrats: 326 (34.79%)
Independents: 388 (41.4%)

28% is an already low percentage and then when they weighted their poll for the demographics, it took the Republican respondents down to 24%. Now try to understand this. IF cBS would have used party affiliation in their weighing - this wouldn't have been an issue, but for some reason cBS didn't use any politcal affiliation weighing for a POLITICAL poll.
Do you think that asking a poll of 24%(weighted) Republicans is going to give you an accurate representation of America?

 

[Czar]

Originally posted by: ShadesOfGrey

Originally posted by: Czar

Originally posted by: ShadesOfGrey

Originally posted by: Czar
ShadesOfGrey,
They did not use a 24% sample of republicans, is that so hard to understand?

They used a 28% sample which was reduced to 24 when they weighted the POLITICAL poll for demographic other than political affiliation.

Figure it out yet? :roll:

No they did not, please understand

They used a sample based on the census data, then asked the questions to those who answered, one regarding their political affiliation or support. After the first phase was done they saw that the respondance sample did not reprisent an accurate relations to the census. So they added new samples based on the same criteria as before, age, sex, and so on. They asked those from the additional sample the same questions, including political affiliation or support which then reduced the total support for the republicans.

Get it now?

Hello!?

Unweighted Total Respondents: 936
Republicans = 259 (27.67%)
Democrats = 326 (34.83%)
Independents = 351 (37.5%)

Weighted Total Respondents: 937
Republicans: 223 (23.80%)
Democrats: 326 (34.79%)
Independents: 388 (41.4%)

28% is an already low percentage and then when they weighted their poll for the demographics, it took the Republican respondents down to 24%. Now try to understand this. IF cBS would have used party affiliation in their weighing - this wouldn't have been an issue, but for some reason cBS didn't use any politcal affiliation weighing for a POLITICAL poll.
Do you think that asking a poll of 24%(weighted) Republicans is going to give you an accurate representation of America?

ok how about I do something even much better, I'll email them and try to get some answers, would that satisfy you?

 

[ShadesOfGrey]

Originally posted by: Czar
ok how about I do something even much better, I'll email them and try to get some answers, would that satisfy you?

Why are you trying to satisfy me? Sorry, but I don't care about you. I posted this story because I'm sick of today's media thinking they can pull this kind of crap. What happened to open and honest reporting? When did it become OK and widly acceptable for activist journalism to be the "news"?

Email them if you'd like. Good luck getting anything other than a form letter response

 

[Czar]

here is the mail I sent

Hi,
Might be unusual to get a question like this from Iceland.

Yesterday you published a poll result you conducted regarding Bush and other political aspects in the US. What struck some people as odd is your use of a weighted sample.

Total Republicans - 259 - 223
Total Democrats - 326 - 326
Total Independents - 351 - 388

First number unweighted and second one weighted. How come the number of republicans decreased and number of independants increased?

I have read various explanations of this but I thought it would be best to get it stright from the people who did the poll. Put a few minds at ease so to say.

With regards,

snippedy snipsnap

we will see how it goes, hope as well as google when I mailed them about abu gharib and their image search, excelent response

 

[totalcommand]

Originally posted by: ShadesOfGrey

Originally posted by: Czar
ShadesOfGrey,
They did not use a 24% sample of republicans, is that so hard to understand?

They used a 28% sample which was reduced to 24 when they weighted the POLITICAL poll for demographic other than political affiliation.

Figure it out yet? :roll:

Everything you keep repeating, over and over and over (as you do in other threads) has been refuted here - give reading a chance. Furthermore, the fact that AP-IPSOS yielded similar numbers backs up the 95% confidence.

Why are you willfully misstating what I wrote? EVERY political group is made of of a complex demographic. I never said otherwise. You seem to think that if the percentage of each political party is correct, nothing else matters. You're completely wrong:

The country consists of 39% Dems, 35% Republicans, and 26% Independents.

But it also consists of (say) 50% Protestants, 30% Catholics, 10% "other Christian", 5% atheists, 3% Jews, 2% Moslems, and 1% "other".

It also consists of 45% College grads, 55% high-school grads, and 10% non-grads.

It also consists of 51% women and 49% men.

It also consists of 25% "over 70", 25% "50 - 70", 30% "30 - 50", and and 20% "18 - 30".

It also consists of 5% "household incomes > $200,000 a year", 20% "$100k to $200K", 25% "$75K to $100K, 20% "$50k to $75K", 20% "$20K - $50K", and 10% "below $20K".

It also consists of 65% "married, straight", 25% "single, straight", 5% "gay, committed", and 5% "gay, non-committed".

It also consists of . . . .

The above figures are just wild-A$$ guesses. The actual values don't matter. What matters is that the demographics of American society are incredibly complex.

And the above figures are just for the overall population. There are also the breakdowns for these groups WITHIN each political group. If you get any of the major demographics wrong, your results will be skewed. Breakdown by political party is just ONE way of choosing the polling sample, and if that is all you look at, your poll will be horribly inaccurate.

But here you are, whining about the political breakdown. You think nothing else is important. You obviously are clueless on the subject of population statistics.

And the fact that you insist that a deviation in the population breakdown is indicative of some agenda on the part of CBS is just absurd.

If CBS had chosen 35% Republicans, but 40% of those Repbulicans had been black, do you think the poll would have been more accurate than, say, a poll consisting of 28% Repulicans of which 5% are black (the "true" percentage)?

Stop writing about subjects you obviously don't understand.

 

[ShadesOfGrey]

Originally posted by: Czar
here is the mail I sent

Hi,
Might be unusual to get a question like this from Iceland.

Yesterday you published a poll result you conducted regarding Bush and other political aspects in the US. What struck some people as odd is your use of a weighted sample.

Total Republicans - 259 - 223
Total Democrats - 326 - 326
Total Independents - 351 - 388

First number unweighted and second one weighted. How come the number of republicans decreased and number of independants increased?

I have read various explanations of this but I thought it would be best to get it stright from the people who did the poll. Put a few minds at ease so to say.

With regards,

snippedy snipsnap

we will see how it goes, hope as well as google when I mailed them about abu gharib and their image search, excelent response

Any response yet? :laugh: I hope so because your buddy totalcommand still doesn't realize he's helping me make my case.

 

[sandorski]

Sigh

 

[Todd33]

Originally posted by: ShadesOfGrey
28% is an already low percentage and then when they weighted their poll for the demographics, it took the Republican respondents down to 24%. Now try to understand this. IF cBS would have used party affiliation in their weighing - this wouldn't have been an issue, but for some reason cBS didn't use any politcal affiliation weighing for a POLITICAL poll.
Do you think that asking a poll of 24%(weighted) Republicans is going to give you an accurate representation of America?

You have no clue about what you are babbling about.

If I do a poll of random people and get 28% Republicans and 28% of the population is Republican, what do I do with my data? Nothing. If you sample at random, it makes no difference what the party Id is, your sample represents the country within error if the sample was random.

Nothing is skewed, the number is 35% +/- 3-4%. There was no media bias, you have yet to show, prove or persuade anything with your 50 replies. Grats on screaming wolf and getting your attention for the week.

 

[ShadesOfGrey]

Originally posted by: Todd33

Originally posted by: ShadesOfGrey
28% is an already low percentage and then when they weighted their poll for the demographics, it took the Republican respondents down to 24%. Now try to understand this. IF cBS would have used party affiliation in their weighing - this wouldn't have been an issue, but for some reason cBS didn't use any politcal affiliation weighing for a POLITICAL poll.
Do you think that asking a poll of 24%(weighted) Republicans is going to give you an accurate representation of America?

You have no clue about what you are babbling about.

If I do a poll of random people and get 28% Republicans and 28% of the population is Republican, what do I do with my data? Nothing. If you sample at random, it makes no difference what the party Id is, your sample represents the country within error if the sample was random.

Nothing is skewed, the number is 35% +/- 3-4%. There was no media bias, you have yet to show, prove or persuade anything with your 50 replies. Grats on screaming wolf and getting your attention for the week.

Someone doesn't know how polling works.:laugh:

Why did they weigh for other demographics if what you say is true?

You people are funny. Still sticking with your willing ignorance.