St Louis Post-Dispatch/KMOV-TV/
7/7-10/08 - 800 LV, 3.5%
Obama 48, McCain 43
I really don't like this poll.
Question 1 is about George Bush. That's going to inflate Obama's numbers every time.
Question 2 asks for whom you voted in the primaries. This is going to hurt Obama's numbers more than McCain's due to the long primary fight, but how much is impossible to say. Enough to counteract the effects in the first question?
I was skeptical to begin with because this poll is the only one showing a meaningful Obama lead in Missouri. We also had 2 polls recently showing very different results. Luckily we have a site like this and 538 to keep us in perspective--this state is still lean McCain for now.
Posted on July 12, 2008 12:38 PM
Edit: I just looked at the chart here for MO and was shocked to see it within 1 point, considering this is only the third poll with an Obama lead (the others showed a 1 and 2 point edge). I guess I should say it's a tossup for the purposes of this site, and only leans McCain at 538 :)
Posted on July 12, 2008 12:52 PM
And this poll is not yet included in the 538 averages. Will make Missouri a complete Toss-Up, with McCain +0.5 or so.
Posted on July 12, 2008 1:14 PM
Very interesting comments about the lead questions. Thanks.
Posted on July 12, 2008 1:15 PM
Right now at 538 McCain is projected to win by 3.4, with a 70% chance of winning the state. One poll when there have been numerous recent polls won't move it that much...probably something like McCain by 2 or 2.5, with a win % over 60. But we'll see what happens soon I'm sure :)
Posted on July 12, 2008 1:26 PM
In terms of poll averages, Pollster.com has McCain +0.7; 538 has McCain between +0.4 and +1.4 depending on statistic used; and RCP has McCain +2.5.
This is the largest Obama advantage in any Missouri poll since Survey USA Feb08.
Posted on July 12, 2008 4:21 PM
Regarding the first question on presidential approval, Rasmussen always leads with this question, and they generally have a small skew to the Republican side from the average. While as Mark has pointed out, studies show that leading with presidential approval (this cycle) or other sorts of questions which can influence later questions can skew results, it does so by a small amount. The weighting of the poll and the quality of the sample itself is more likely to introduce error.
Obviously this poll is an outlier, but I doubt it's primarily due to the first question.
Posted on July 12, 2008 8:15 PM
Comments: (you may use HTML tags for style)
Please be patient while your comment posts - sometimes it takes a minute or two. To check your comment, please wait 60 seconds and click your browser's refresh button. Note that comments with three or more hyperlinks will be held for approval.
Please email us to report offensive comments.
See our comment policy here. Note that we require commenters to share their email address via Typekey. We will never share your email address with anyone without your explicit permission.
MAP - US, AL, AK, AZ, AR, CA, CO, CT, DE, FL, GA, HI, ID, IL, IN, IA, KS, KY, LA, ME, MD, MA, MI, MN, MS, MO, MT, NE, NV, NH, NJ, NM, NY, NC, ND, OH, OK, OR, PA, RI, SC, SD, TN, TX, UT, VT, VA, WA, WV, WI, WY, PR