Free Republic
Browse · Search
News/Activism
Topics · Post Article

To: SoFloFreeper

Fatal Flaw....Romney winning women by 3% and losing men by 7%? That is where you see a sampling error. And a fairly substantial one I would say.


109 posted on 09/29/2012 10:24:30 PM PDT by johncocktoasten (Practicing asymetrical thread warfare against anti-Palin Trolls)
[ Post Reply | Private Reply | To 7 | View Replies ]


To: johncocktoasten

Polls aren’t necessarily accurate when divided up into smaller demographic groups. That doesn’t mean the overall total isn’t accurate. Naturally, the sample of men or women in the poll is only half the total sample. And if the total sample was just the minimum quantity needed to be accurate, half of the total will be only half what is needed to be accurate about each gender’s preferences. Rasmussen would need to double his original sample size in order to get accurate numbers for each gender. Otherwise the original poll can only be accurate for the group it defines, i.e. voters, not for smaller sub-groups within it.


112 posted on 09/29/2012 10:29:27 PM PDT by JediJones (KARL ROVE: "And remember, this year, no one is seriously talking about ending abortion.")
[ Post Reply | Private Reply | To 109 | View Replies ]

Free Republic
Browse · Search
News/Activism
Topics · Post Article


FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson