|
Title: Poll chat and adjustments Post by: Torie on May 30, 2012, 03:52:05 PM Nate Silver has an interesting article (http://www.fivethirtyeight.com/2010/07/senate-forecast-718-republican-outlook.html?utm_source=twitterfeed&utm_medium=twitter) which you may have missed from 2010, where he explains per his regression analysis how converts polls of all adults, registered voters and likely voters into an apple to apples comparison (Dems do 7 points better with all adult polls, and 4 points better with registered voters). The Rasmussen "house effect" is 2 to 3 points. He also says PVI isn't as good as party identification. I just thought that you poll junkies might be interested. Whether the same adjustment percentages obtain this year, is of course an issue.
Title: Re: Poll chat and adjustments Post by: Minnesota Mike on May 30, 2012, 06:09:53 PM But presidential election years are different than than non presidential years. The higher turnout in presidential years would seem likely to me to narrow the difference between Likely Voter and Registered Voter polls.
Title: Re: Poll chat and adjustments Post by: NVGonzalez on May 31, 2012, 02:07:13 AM Also this may be somewhat off-topic but I think it is a good idea to not only look at the party sample but also at the demographic sample. For example the Florida poll that came out recently while it had Democrats over sampled so were seniors.
|