Comments on: How to Read Polls http://www.danvk.org/wp/2008-09-25/how-to-read-polls/ Keepin' static like wool fabric since 2006 Wed, 08 Oct 2014 14:33:23 +0000 hourly 1 http://wordpress.org/?v=3.9.2 By: Spencer http://www.danvk.org/wp/2008-09-25/how-to-read-polls/comment-page-1/#comment-14944 Wed, 26 Nov 2008 20:46:31 +0000 http://www.danvk.org/wp/?p=302#comment-14944 Wow, I found this fascinating! Great explanation. Who knew that statistics could be manipulated in so many ways… (hint of sarcasm)

]]>
By: danvk http://www.danvk.org/wp/2008-09-25/how-to-read-polls/comment-page-1/#comment-13402 Sun, 28 Sep 2008 19:32:06 +0000 http://www.danvk.org/wp/?p=302#comment-13402 That would be true if the pollsters reported a standard deviation, the formula for which is:

sigma = sqrt(p * (1-p) / N)

But what they’re really reporting is 1/sqrt(N). Whether that quantity should be referred to as a “margin of error” is mostly semantics. It’s the quantity that’s reported, so it’s the quantity I based my calculations on.

]]>
By: starwed http://www.danvk.org/wp/2008-09-25/how-to-read-polls/comment-page-1/#comment-13384 Sun, 28 Sep 2008 07:11:48 +0000 http://www.danvk.org/wp/?p=302#comment-13384 I believe you made an error here…

The margin of error depends not only on the sample size, but also the recorded result: Margin of error

]]>
By: danvk http://www.danvk.org/wp/2008-09-25/how-to-read-polls/comment-page-1/#comment-13302 Fri, 26 Sep 2008 18:05:31 +0000 http://www.danvk.org/wp/?p=302#comment-13302 That’s a really interesting podcast. I wonder what the real margin of error would look like on one of these polls.

I figured out where the 1.644 was coming from. It’s equal to

sqrt(2) * erfinv(2*0.95 – 1) = 1.64485

Plug in values other than 0.95 to get other confidence levels.

]]>
By: Matt Rosencrantz http://www.danvk.org/wp/2008-09-25/how-to-read-polls/comment-page-1/#comment-13263 Fri, 26 Sep 2008 04:54:28 +0000 http://www.danvk.org/wp/?p=302#comment-13263 I found this podcast:
http://www.econtalk.org/archives/2008/07/rivers_on_polli.html

fascinating on why these margins of error systematically underestimate the true uncertainty. Of course I don’t know anything about the particular poll you are pointing too, but if what this speaker says is true, sloppy statistics are pretty pervasive. In particular the part about not adjusting error calculations for sample re-weighting.

]]>