I Hate Polls!

[Pete7469]

The polls are designed to influence public opinion, not to report on it.

It is statistically ridiculous to claim that a poll of 1000 people accurately reflects the opinions of 330,000,000 people.

its a game. the only winners are the pollsters who are paid to "do a poll for me that proves X".

I'm confident you're totally right.

They still insist Jeb polls near the top, but I don't know ANYONE who want's that clown elected.

 

[bendog]

The polls are designed to influence public opinion, not to report on it.

It is statistically ridiculous to claim that a poll of 1000 people accurately reflects the opinions of 330,000,000 people.

its a game. the only winners are the pollsters who are paid to "do a poll for me that proves X".

I'm confident you're totally right.

They still insist Jeb polls near the top, but I don't know ANYONE who want's that clown elected.

What polls show Jebbie "near the top?" LOL

 

[Toro]

Yes, they did and what I said is statistically correct. Figures don't lie but liars figure.

a 5% random sample is needed for a poll to be statistically meaningful. The pollsters try to get around that by saying their sample is not random but proportionally represents every faction in the total population. For example if 1% of the population is gay males who support the right to life then they must have 1 of them in every hundred sampled, and so forth for every possible faction in the country. Its foolishness, but you are free to buy into it if you want to.

It's an odd assertion to make, given that corporations spend billions of dollars a year using similar sampling methodologies to understand the consumer market. Why would corporations and pollsters spend all that money if it's worthless?

pinqy , Statistikhengst Darkwind

I'm almost certain that you aren't correct, so I've called in an economist and a few who know a bit about polls.

This is the math that I remember from statistics

The estimator of a proportion is

, where X is the number of 'positive' observations (e.g. the number of people out of the n sampled people who are at least 65 years old). ...

For sufficiently large n, the distribution of

will be closely approximated by a normal distribution.[2] Using this approximation, it can be shown that around 95% of this distribution's probability lies within 2 standard deviations of the mean. Using the Wald method for the binomial distribution, an interval of the form

will form a 95% confidence interval for the true proportion. If this interval needs to be no more than W units wide, the equation

can be solved for n, yielding[3][4] n = 4/W2 = 1/B2 where B is the error bound on the estimate, i.e., the estimate is usually given as within ± B. So, for B = 10% one requires n = 100, for B = 5% one needs n = 400, for B = 3% the requirement approximates to n = 1000, while for B = 1% a sample size of n = 10000 is required. These numbers are quoted often in news reports of opinion polls and other sample surveys.​

Sample size determination - Wikipedia, the free encyclopedia

Also

How many people are there in the group your sample represents? This may be the number of people in a city you are studying, the number of people who buy new cars, etc. Often you may not know the exact population size. This is not a problem. The mathematics of probability proves the size of the population is irrelevant unless the size of the sample exceeds a few percent of the total population you are examining. This means that a sample of 500 people is equally useful in examining the opinions of a state of 15,000,000 as it would a city of 100,000. For this reason, The Survey System ignores the population size when it is "large" or unknown. Population size is only likely to be a factor when you work with a relatively small and known group of people (e.g., the members of an association).

The confidence interval calculations assume you have a genuine random sample of the relevant population. If your sample is not truly random, you cannot rely on the intervals. Non-random samples usually result from some flaw in the sampling procedure. An example of such a flaw is to only call people during the day and miss almost everyone who works. For most purposes, the non-working population cannot be assumed to accurately represent the entire (working and non-working) population.​

Sample Size Calculator - Confidence Level, Confidence Interval, Sample Size, Population Size, Relevant Population - Creative Research Systems

 

[Redfish]

"It is statistically ridiculous..."

If you really believe this you are a statistical ignoramous. A properly taken, un-biased poll of 100 people could EASILY come within a percent or two on a one-of-two question.

You can argue about the integrity of the pollsters, the difficulty of getting a true random sampling, or whether the questions asked are relevant, but random sampling is incredibly accurate, as anyone who has taken even a single stats course will attest.

I suggest that you go to your local library and check out a stat 101 text. Then read it. You will learn that for a sample to be truly representative of the total population it must be truly random and at least 5%. I understand how the pollsters claim that they overcome that by selecting their tiny samples to represent all factions, but its bullshit. A sample of 1000 out of 330,000,000 is STATISTICALLY RIDICULOUS. There is simply no way that they can proportionately represent all of the many factions in the US in a sample of 1000. Its a joke, but if you want to believe it, go right ahead. The pollsters are getting rich because of ignorance like yours.

Man, I have taken more than Stat 101, and you are completely wrong. Speak on things you actually know something about, if there is such a thing, because you obviously know nothing of statistics.

You must have slept through the class, because you know absolutely nothing about statistical sampling.

 

[Redfish]

Yes, they did and what I said is statistically correct. Figures don't lie but liars figure.

a 5% random sample is needed for a poll to be statistically meaningful. The pollsters try to get around that by saying their sample is not random but proportionally represents every faction in the total population. For example if 1% of the population is gay males who support the right to life then they must have 1 of them in every hundred sampled, and so forth for every possible faction in the country. Its foolishness, but you are free to buy into it if you want to.

It's an odd assertion to make, given that corporations spend billions of dollars a year using similar sampling methodologies to understand the consumer market. Why would corporations and pollsters spend all that money if it's worthless?

pinqy , Statistikhengst Darkwind

I'm almost certain that you aren't correct, so I've called in an economist and a few who know a bit about polls.

This is the math that I remember from statistics

The estimator of a proportion is

, where X is the number of 'positive' observations (e.g. the number of people out of the n sampled people who are at least 65 years old). ...

For sufficiently large n, the distribution of

will be closely approximated by a normal distribution.[2] Using this approximation, it can be shown that around 95% of this distribution's probability lies within 2 standard deviations of the mean. Using the Wald method for the binomial distribution, an interval of the form

will form a 95% confidence interval for the true proportion. If this interval needs to be no more than W units wide, the equation

can be solved for n, yielding[3][4] n = 4/W2 = 1/B2 where B is the error bound on the estimate, i.e., the estimate is usually given as within ± B. So, for B = 10% one requires n = 100, for B = 5% one needs n = 400, for B = 3% the requirement approximates to n = 1000, while for B = 1% a sample size of n = 10000 is required. These numbers are quoted often in news reports of opinion polls and other sample surveys.​

Sample size determination - Wikipedia, the free encyclopedia

Also

How many people are there in the group your sample represents? This may be the number of people in a city you are studying, the number of people who buy new cars, etc. Often you may not know the exact population size. This is not a problem. The mathematics of probability proves the size of the population is irrelevant unless the size of the sample exceeds a few percent of the total population you are examining. This means that a sample of 500 people is equally useful in examining the opinions of a state of 15,000,000 as it would a city of 100,000. For this reason, The Survey System ignores the population size when it is "large" or unknown. Population size is only likely to be a factor when you work with a relatively small and known group of people (e.g., the members of an association).

The confidence interval calculations assume you have a genuine random sample of the relevant population. If your sample is not truly random, you cannot rely on the intervals. Non-random samples usually result from some flaw in the sampling procedure. An example of such a flaw is to only call people during the day and miss almost everyone who works. For most purposes, the non-working population cannot be assumed to accurately represent the entire (working and non-working) population.​

Sample Size Calculator - Confidence Level, Confidence Interval, Sample Size, Population Size, Relevant Population - Creative Research Systems

I fully understand that that is the new math of statistics. But its mathematical bunk. Its a creation of the pollsters in order to continue their farse.

As I said earlier, today's polls are designed to influence public opinion, not to report on it.

But you are free to buy the BS if you choose.

 

[Toro]

Yes, they did and what I said is statistically correct. Figures don't lie but liars figure.

a 5% random sample is needed for a poll to be statistically meaningful. The pollsters try to get around that by saying their sample is not random but proportionally represents every faction in the total population. For example if 1% of the population is gay males who support the right to life then they must have 1 of them in every hundred sampled, and so forth for every possible faction in the country. Its foolishness, but you are free to buy into it if you want to.

It's an odd assertion to make, given that corporations spend billions of dollars a year using similar sampling methodologies to understand the consumer market. Why would corporations and pollsters spend all that money if it's worthless?

pinqy , Statistikhengst Darkwind

I'm almost certain that you aren't correct, so I've called in an economist and a few who know a bit about polls.

This is the math that I remember from statistics

The estimator of a proportion is

, where X is the number of 'positive' observations (e.g. the number of people out of the n sampled people who are at least 65 years old). ...

For sufficiently large n, the distribution of

will be closely approximated by a normal distribution.[2] Using this approximation, it can be shown that around 95% of this distribution's probability lies within 2 standard deviations of the mean. Using the Wald method for the binomial distribution, an interval of the form

will form a 95% confidence interval for the true proportion. If this interval needs to be no more than W units wide, the equation

can be solved for n, yielding[3][4] n = 4/W2 = 1/B2 where B is the error bound on the estimate, i.e., the estimate is usually given as within ± B. So, for B = 10% one requires n = 100, for B = 5% one needs n = 400, for B = 3% the requirement approximates to n = 1000, while for B = 1% a sample size of n = 10000 is required. These numbers are quoted often in news reports of opinion polls and other sample surveys.​

Sample size determination - Wikipedia, the free encyclopedia

Also

How many people are there in the group your sample represents? This may be the number of people in a city you are studying, the number of people who buy new cars, etc. Often you may not know the exact population size. This is not a problem. The mathematics of probability proves the size of the population is irrelevant unless the size of the sample exceeds a few percent of the total population you are examining. This means that a sample of 500 people is equally useful in examining the opinions of a state of 15,000,000 as it would a city of 100,000. For this reason, The Survey System ignores the population size when it is "large" or unknown. Population size is only likely to be a factor when you work with a relatively small and known group of people (e.g., the members of an association).

The confidence interval calculations assume you have a genuine random sample of the relevant population. If your sample is not truly random, you cannot rely on the intervals. Non-random samples usually result from some flaw in the sampling procedure. An example of such a flaw is to only call people during the day and miss almost everyone who works. For most purposes, the non-working population cannot be assumed to accurately represent the entire (working and non-working) population.​

Sample Size Calculator - Confidence Level, Confidence Interval, Sample Size, Population Size, Relevant Population - Creative Research Systems

I fully understand that that is the new math of statistics. But its mathematical bunk. Its a creation of the pollsters in order to continue their farse.

As I said earlier, today's polls are designed to influence public opinion, not to report on it.

But you are free to buy the BS if you choose.

So I guess the liberal media wants Trump as President!

 

[Redfish]

Yes, they did and what I said is statistically correct. Figures don't lie but liars figure.

a 5% random sample is needed for a poll to be statistically meaningful. The pollsters try to get around that by saying their sample is not random but proportionally represents every faction in the total population. For example if 1% of the population is gay males who support the right to life then they must have 1 of them in every hundred sampled, and so forth for every possible faction in the country. Its foolishness, but you are free to buy into it if you want to.

It's an odd assertion to make, given that corporations spend billions of dollars a year using similar sampling methodologies to understand the consumer market. Why would corporations and pollsters spend all that money if it's worthless?

pinqy , Statistikhengst Darkwind

I'm almost certain that you aren't correct, so I've called in an economist and a few who know a bit about polls.

This is the math that I remember from statistics

The estimator of a proportion is

, where X is the number of 'positive' observations (e.g. the number of people out of the n sampled people who are at least 65 years old). ...

For sufficiently large n, the distribution of

will be closely approximated by a normal distribution.[2] Using this approximation, it can be shown that around 95% of this distribution's probability lies within 2 standard deviations of the mean. Using the Wald method for the binomial distribution, an interval of the form

will form a 95% confidence interval for the true proportion. If this interval needs to be no more than W units wide, the equation

can be solved for n, yielding[3][4] n = 4/W2 = 1/B2 where B is the error bound on the estimate, i.e., the estimate is usually given as within ± B. So, for B = 10% one requires n = 100, for B = 5% one needs n = 400, for B = 3% the requirement approximates to n = 1000, while for B = 1% a sample size of n = 10000 is required. These numbers are quoted often in news reports of opinion polls and other sample surveys.​

Sample size determination - Wikipedia, the free encyclopedia

Also

How many people are there in the group your sample represents? This may be the number of people in a city you are studying, the number of people who buy new cars, etc. Often you may not know the exact population size. This is not a problem. The mathematics of probability proves the size of the population is irrelevant unless the size of the sample exceeds a few percent of the total population you are examining. This means that a sample of 500 people is equally useful in examining the opinions of a state of 15,000,000 as it would a city of 100,000. For this reason, The Survey System ignores the population size when it is "large" or unknown. Population size is only likely to be a factor when you work with a relatively small and known group of people (e.g., the members of an association).

The confidence interval calculations assume you have a genuine random sample of the relevant population. If your sample is not truly random, you cannot rely on the intervals. Non-random samples usually result from some flaw in the sampling procedure. An example of such a flaw is to only call people during the day and miss almost everyone who works. For most purposes, the non-working population cannot be assumed to accurately represent the entire (working and non-working) population.​

Sample Size Calculator - Confidence Level, Confidence Interval, Sample Size, Population Size, Relevant Population - Creative Research Systems

I fully understand that that is the new math of statistics. But its mathematical bunk. Its a creation of the pollsters in order to continue their farse.

As I said earlier, today's polls are designed to influence public opinion, not to report on it.

But you are free to buy the BS if you choose.

So I guess the liberal media wants Trump as President!

I don't know, they should. I haven't seen any polls showing him winning the general election, just the GOP primaries.

 

[longknife]

After all the above comments, it appears to all come down to the fact that, for purposes of trying to have things skewed their way, groups both political and industrial pay groups of so-called experts to conduct a crap shoot to tell them what to do!

Right?