[1-Eagle]

Thanks for explaining that a "margin for error" is actually a fabricated "indicator". But this is not how it is used. It is used by pollsters and "journalists" to indicate an imagined degree of accuracy, even referring to the results as being "within the margin of error". In 1996, approximately 15 polls were so badly off their predictions that they were WAY outside of their margins of error, some even more than 10% outside the margin. Only 2 were inside their margins of error, one of those being Zogby.

So "margins of error" were proven to be nothing but figments of the pollsters imaginations in 1996. And so the polls that showed Dole would lose to Clinton by 20% or 18% had so much egg on their faces when he lost by around 8%. A British journalist observing all this wrote that if the polls and media had not been so skewed and slanted against him, Dole/Kemp might have had a chance.

[AndyTheBear]

It does indeed drive me nuts when I hear the talking heads saying "outside the Margin of Error" as if it means much. But I don't think its accurate to say they are figments of the imagination. It is a real thing used in probability theory. Its just not useful to know, and is misleading when it comes to political polls.