Active Now

Shuhak
Discussion » Statements » Rosie's Corner » We hear about "Margin of/for error" in poll numbers. Why is there a need for one? Who decides what the percentages should be and what does margin of/for error include?

We hear about "Margin of/for error" in poll numbers. Why is there a need for one? Who decides what the percentages should be and what does margin of/for error include?

.

Posted - August 25, 2016

Responses


  • 691

    Math decides, assuming a representative sample.  The larger your sample becomes the better, as long as it is representative.  The margin of error is not nearly as important as the confidence interval quoted, that is when they say 19 times out of 20 or so.  It is expected the results will not be accurate in that 1 time out of 20.  As I keep saying this relies on a representative sample who answer honestly which is very hard to get and it is why outcomes often don't match polls.

      August 25, 2016 1:42 PM MDT
    0

  • 1113
    Your poll would only be perfectly accurate if it included every single person of the group the poll refers to. If the question is "Who do Americans like for the 2016 Election", and you asked every single American, then your margin of error would be zero. this never happens. The polls might ask 1000 people at random. That's a decent sample, but there is a chance that you happened to ask 1000 people who were disproportiately biased towards one candidate or another. That's what margin of error represents. If you asked 10,000 people your margin of error would be smaller, because it's less likely that you'd randomly select such a large group that had a strong bias. If your poll was only 100 people, or 10 people, then your margin of error would get much bigger.
      August 25, 2016 2:20 PM MDT
    0

  • 113301

    Thank you for your helpful reply ITpro. I appreciate it. It other words it's kinda complicated. Happy Friday! :)

      August 26, 2016 2:54 AM MDT
    0

  • 113301

    This is an extremely helpful reply Rpf for which I thank you. I get your point. That would be assuming people tell the truth. Ever hear about "the Bradley" effect? There was an African American running for political office and polling showed him winning. But he lost. That was because people did not want to admit they wouldn't vote for someone of color so they lied. I suppose the lie could go in the opposite direction aa well. Some folks say they won't vote for Trump but they might just be afraid to say so and when they vote he will get those votes. So it's a crapshoot isn't it? Just what we need. More uncertainty! :(

      August 26, 2016 2:57 AM MDT
    0