A new poll, by Majority Watch, shows Democratic challenger Phil Kellam leading Republican incumbent Thelma Drake 51% to 43%, with 6% undecided. The poll was conducted August 27-29 with a sample size of 1,021 and a margin of error of +/- 3.1%.
Here is what the website said about the methodology for this poll:
The Majority Watch polls, a project of RT Strategies and Constituent Dynamics, comprise polls conducted using interactive voice recognition (IVR) technology over the telephone. In each of 30 contested U.S. House Congressional districts (CDs), a representative sample of about 1,000 voters were selected from voter lists provided by each state. The interviews were conducted August 27-30, 2006. Results were weighted to represent the likely electorate by demographic factors such as age, sex, race and geographic location in the CD. No more than one time in 20 should chance variations in the sample cause the results to vary by more than 3 percentage points from the answers that would be obtained if all voters in a CD were polled.
Looking at the crosstabs, I can only assume that this was not the 3-question poll I participated in last week 😦 This one has a lot more information in it than I was asked.
The crosstabs also reveal that Kellam may be in even better shape. When looking only at likely voters (821 of the 1,021 people polled), Kellam leads 54% to 41%.
Some other interesting tidbits from the crosstabs:
- Only 22% of Republicans support Kellam. I’m a bit surprised that this number isn’t higher since Kellam has been actively courting such support but it is closer to what I have been hearing from Republicans I know around the area.
- 90% of those who approve of Bush (about 38%) are supporting Drake. 85% of those who disapprove are supporting Kellam. It appears that Kellam is riding the wave of voter discontent with the Bush administration.
- Both women and men favor Kellam over Drake. White voters are evenly split between the two. Nonwhite voters favor Kellam by a huge margin – 59% to 19%, perhaps due to the fact that 60% of the nonwhite voters consider themselves Democrats.
I suspect the Kellam camp will be quite happy with these numbers.
h/t to Rob over at RK
Technorati Tags: Phil Kellam, Thelma Drake
VIVIAN J. PAIGE | All Politics is Local 
Well, if you made an A+, then you know that the Drake poll sample size is too small and the margin of error too large 🙂 No need for any more statistical analysis skills than that 😉
Look – this poll is valid. But as I said before, I don’t put much stock in polls. It’s kinda like a balance sheet – a snapshot in time. Tomorrow, or next week, the cash may be all gone (or, in this case, the lead may vanish).
As far as I know, you won’t see a poll with a 99% confidence level. (I’ve never seen one.) They are usually 95%. That’s why the MofE is larger than what would be acceptable in an audit environment.
I know. I was kidding.
I do, however, still think the race is closer than 8%, for either side. I think it is still around 52-48%, and I don’t know who has 52. I am waiting for a more well known independent poll.
Mason-Dixon was supposed to be coming out at some point with new predictions for the Senate race, maybe next week.