Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

tableturner

(1,684 posts)
Wed Oct 24, 2012, 12:49 PM Oct 2012

Rand Poll shows good news!

The Rand Poll surveys the same group of people over and over, with one seventh of them surveyed each day on the same day of each week. The poll results reported today show the first effects of polling done after the last debate, meaning that one seventh of the respondents were surveyed yesterday, the first day after the debate.

Romney's numbers went down from 46.36% to 45.34%, more than 1%, which looks to be the second largest one day drop the survey has ever shown for him, and the survey started on 7-11. Remember, this is the result of only one seventh of the respondents having given a new response after the debate.

Obama's numbers went up from 48.26% to 49.19%, almost a full percentage point, which after a cursory look seems to be the third or fourth highest one day jump for Obama since the survey started on 7-11.

https://mmicdata.rand.org/alp/?page=election

4 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
Rand Poll shows good news! (Original Post) tableturner Oct 2012 OP
Kick to engender mood enhancement effects! tableturner Oct 2012 #1
The Rand method (longitudinal study of same voters) is the future of polling. reformist2 Oct 2012 #2
It IS a really good way to do a poll...... tableturner Oct 2012 #3
Kick for the evening crowd..... tableturner Oct 2012 #4

tableturner

(1,684 posts)
3. It IS a really good way to do a poll......
Wed Oct 24, 2012, 01:29 PM
Oct 2012

.....because it is an apples to apples view, which more accurately shows the effects of ongoing events during the election cycle. Using a more random method, you cannot really tell how much of a poll's changing results is due to the effects of events or due to the effects of different people being surveyed.

Latest Discussions»General Discussion»Rand Poll shows good news...