Poll: U.S. sees Obama as liberal

[Demit]

26. This is interesting, the survey methods—

I'm replying to you, Vincardog, so that this info will be towards the top of the thread

"Survey Methods

Results for this USA Today/Gallup poll are based on telephone interviews conducted Dec. 15-18, 2011, with a random sample of 1,019 adults, aged 18 and older, living in all 50 U.S. states and the District of Columbia.

For results based on the total sample of national adults, one can say with 95% confidence that the maximum margin of sampling error is ±4 percentage points.

For results based on the total sample of 284 Democrats, one can say with 95% confidence that the maximum margin of sampling error is ±7 percentage points.

For results based on the total sample of 303 Republicans, one can say with 95% confidence that the maximum margin of sampling error is ±7 percentage points.

For results based on the total sample of 406 independents, one can say with 95% confidence that the maximum margin of sampling error is ±6 percentage points.

...
In addition to sampling error, question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of public opinion polls."


The margins of error for those three groups are sizable, but how on earth (I'm not a statistician) do they average out to a total MoE of ±4? And yes, asking people to self-report, or self identify, gives you misleading information. It's completely unreliable. Except, of course, for pushing an idea by presenting it as 'scientific'.