• MxM111@kbin.social
      link
      fedilink
      arrow-up
      1
      arrow-down
      1
      ·
      edit-2
      7 months ago

      Why don’t you educate me? This is for sure not 95% confidence interval nor 3 sigma. This might be 80% but this is close enough to one sigma.

      The reason why I said it is std, is because suppose that you have a single person instead of 1000. If we expect the actual numbers to be about 50% for Biden or Trump, then with one person you get 100% or 0%, which is +/-50% error over 50% median. Which gives std of 1. After that, std decreases as 1/sqrt(1000).

      I understand that I might miss there small factors, but I could not be that far from correct answer. Where do I went wrong?