America is conservative

[Nor_Cal_Angler]

Actually, sitting outside your local store would provide a non-random sample of people shopping in your store who agreed to talk with you. It would not be projectable to any broader population at all. The reason samples taken over the course of a year cannot be added together is because you are measuring a moving target: public opinion. If you were measuring hair color, a sample taken over the course of a year would not be bad.

All in all, this is like talking to those who condemn FF and e-collars without ever having done or used either or having seen the results. Both tools can be used inappropriately. However, those who simply oppose them out of ignorance are only showing what they don't know.

Yes it would be a random sample...I am not asking them questions about where they normally shop...and them agreeing to talk with me is the same as peopel answering a phone call or not...just as the numbers assigned to call a home are a random sample and if people decided to talk is as well.

Jesus Cristo...your hung up on this add them together issue..I never added the results of TWO DIFFERENT POLLS...you did read the article..(assuming).it is the same poll and I gave the numbers as a whole total population....instead of how they presented them...on a month and year total....Just like in math...the same poll and same questions asked over the course of 7years and 9 months is the same as asking 1.395 million people the same question...and you can keep trying to insult me and or my intelligence all you want with your big words and thinking I am not quick witted enough to read "those who condemn FF and E-collars with out ever having done or used either or having seen the results" followed by..."However, those who simply oppose them out of ignorance are only showing what they don't know"

Like people who condemn Digital SLR....bla bla bla....

twist it how ever you want....america is not becomming more conservative.

NCA

[dnf777]

Yes it would be a random sample...I am not asking them questions about where they normally shop...and them agreeing to talk with me is the same as peopel answering a phone call or not...just as the numbers assigned to call a home are a random sample and if people decided to talk is as well.

Jesus Cristo...your hung up on this add them together issue..I never added the results of TWO DIFFERENT POLLS...you did read the article..(assuming).it is the same poll and I gave the numbers as a whole total population....instead of how they presented them...on a month and year total....Just like in math...the same poll and same questions asked over the course of 7years and 9 months is the same as asking 1.395 million people the same question...and you can keep trying to insult me and or my intelligence all you want with your big words and thinking I am not quick witted enough to read "those who condemn FF and E-collars with out ever having done or used either or having seen the results" followed by..."However, those who simply oppose them out of ignorance are only showing what they don't know"

Like people who condemn Digital SLR....bla bla bla....

twist it how ever you want....america is not becomming more conservative.

NCA

In regards to polling only, (not the specific issue here) Standing outside a store polling is NOT random. You have excluded many elderly people who have others shop for them, or very poor people who don't own cars. Then, which store...Whole Foods in a nice suburb...or Stop-N-Rob in the ghetto?
Phone surveys survey only those who have phones and don't have them shut off, or excludes harder-working americans who are rarely at home, and may use cell phones on the road.....Many doctors, lawyers, and other professionals choose to be unlisted, and therefore won't be included in a "randomly" generated list.

Lots of BS, I know, but a TRUE random survey is a rare breed, indeed! Selection bias is like mosquitoes, no matter how hard you try, you can't get rid of all of 'em.

[BonMallari]

I think one thing that has not been pointed out is the obvious..the groups that commission (pay for) these polls expect a desired result to support their premise, thesis,political stance. When Rasmussen, or Lundsford poll they are doing so for Fox, CNN uses Gallup or Harris as does USA Today, both political sides use them, both spin them the way they want, and obviously the only poll that counts is the one on election day

But in Today's world peoples opinions are easily swayed and can be changed in an instant, polls can influence people to vote for a candidate, just because its the popular thing to do and many people all want to say they voted for the winner, but will disclaim that winner if things go south

[YardleyLabs]

I think one thing that has not been pointed out is the obvious..the groups that commission (pay for) these polls expect a desired result to support their premise, thesis,political stance. When Rasmussen, or Lundsford poll they are doing so for Fox, CNN uses Gallup or Harris as does USA Today, both political sides use them, both spin them the way they want, and obviously the only poll that counts is the one on election day

But in Today's world peoples opinions are easily swayed and can be changed in an instant, polls can influence people to vote for a candidate, just because its the popular thing to do and many people all want to say they voted for the winner, but will disclaim that winner if things go south

You are of course correct. Rasmussen, for example, does polling for Republican campaigns. Gallup by contrast accepts no contracts with political parties or political candidates. All the major pollsters partner with news organizations, and all earn a large portion (usually the majority) of their revenues from commercial clients seeking information of products under development or being marketed. Gallup actually began as a business serving movie companies in the 1930's trying to measure audience appeal of different movies. While the ultimate objective of polling is to provide the client with tools to help influence opinions, the legitimate companies will not accept contracts that are seeking biased results for push marketing.

[Nor_Cal_Angler]

And so...the truth finally comes out...

the poll origionally posted and my reference to Rassmus, can be summed up as

BS...I think that was my origional POINT.

or there again, my point could also be that a poll with 1000000 people I FEEL is more accurate than a poll with 1000, which ever way you dice it. I dont care about your "theories of probability" or "probability theories" both of which coincidently happen to only be THEORIES which could translate to FAITH (in your research about your THEORY)

Fact is...if you asked people hey, did you know that Americans love the symbol ? more than the symbol !...and the person asked you well how do you know..

and your explaination was..well I gathered data from 1000 people.

Most common sense, semi educated, warm blooded people are gonna LAUGH at you, for trying to make that fit the bill of AMERICA.

just saying....thats my THEROY.

NCA

PS..Jeff it has been fun, but sometimes just sometimes, I see right through the fog no hard feelings its all in good conversation.

[dnf777]

I think one thing that has not been pointed out is the obvious..the groups that commission (pay for) these polls expect a desired result to support their premise, thesis,political stance. When Rasmussen, or Lundsford poll they are doing so for Fox, CNN uses Gallup or Harris as does USA Today, both political sides use them, both spin them the way they want, and obviously the only poll that counts is the one on election day

But in Today's world peoples opinions are easily swayed and can be changed in an instant, polls can influence people to vote for a candidate, just because its the popular thing to do and many people all want to say they voted for the winner, but will disclaim that winner if things go south

So true. Polls that are commissioned to help guide campaigns need to be honest and true. Polls that are released through the media in attempts to sway or influence people or policy do NOT.

When reading the medical literature, I have an entire algorithm I go through before even reading the substance! Sometimes, the bias resides not in the polls or studies themselves, but in the selective publishing or scrapping process. If I see a journal with front and back leaf glossy ads for a drug or product, I won't expect to see any studies accepted for publication that is not favorable towards those products. Obviously, some journals and media outlets are more scrupulous than others, but we've seen even the "big boys" get pie on their faces. Ah, just another by-product of capitalism!

[YardleyLabs]

And so...the truth finally comes out...

the poll origionally posted and my reference to Rassmus, can be summed up as

BS...I think that was my origional POINT.

or there again, my point could also be that a poll with 1000000 people I FEEL is more accurate than a poll with 1000, which ever way you dice it. I dont care about your "theories of probability" or "probability theories" both of which coincidently happen to only be THEORIES which could translate to FAITH (in your research about your THEORY)

Fact is...if you asked people hey, did you know that Americans love the symbol ? more than the symbol !...and the person asked you well how do you know..

and your explaination was..well I gathered data from 1000 people.

Most common sense, semi educated, warm blooded people are gonna LAUGH at you, for trying to make that fit the bill of AMERICA.

just saying....thats my THEROY.

NCA

PS..Jeff it has been fun, but sometimes just sometimes, I see right through the fog no hard feelings its all in good conversation.

NCA,

When it comes to polling and the factors that make them more or less accurate, your understanding is so far away from reality that I don't even know where to begin in trying to get you to understand the issues.

People have been studying ways to improve polling for around 70 years. For the most part, they take their work pretty seriously and conform to very high standards scientific research. You begin by assuming that they all have the intellectual ethics of an O'Reilly or Hannity or Beck or Sharpton or Geraldo Rivera (i.e. none).

My own knowledge in these areas is limited. However, I did spend a few years in graduate school studying sampling and polling techniques including preparing critiques of a number of political surveys, and I have prepared the statistical arguments for expert testimony on sampling techniques for a few court cases. Unfortunately, what makes statistical studies so easy to manipulate is a combination of gullibility and the willingness of so many to excuse fraud as long as its practitioners are selling the "right" kind of snake oil.

[mjh345]

And so...the truth finally comes out...

the poll origionally posted and my reference to Rassmus, can be summed up as

BS...I think that was my origional POINT.

or there again, my point could also be that a poll with 1000000 people I FEEL is more accurate than a poll with 1000, which ever way you dice it. I dont care about your "theories of probability" or "probability theories" both of which coincidently happen to only be THEORIES which could translate to FAITH (in your research about your THEORY)

Fact is...if you asked people hey, did you know that Americans love the symbol ? more than the symbol !...and the person asked you well how do you know..

and your explaination was..well I gathered data from 1000 people.

Most common sense, semi educated, warm blooded people are gonna LAUGH at you, for trying to make that fit the bill of AMERICA.

just saying....thats my THEROY.

NCA

PS..Jeff it has been fun, but sometimes just sometimes, I see right through the fog no hard feelings its all in good conversation.

HUUNNHH??!!

[Nor_Cal_Angler]

you know sometimes the people that are, how should I say "book smart"

cant see beyond the end of the next paragraph.

NCA

[YardleyLabs]

you know sometimes the people that are, how should I say "book smart"

cant see beyond the end of the next paragraph.

NCA

NCA,

I agree completely. But that doesn't mean they are alway wrong. Have a good day.