Mark Blumenthal | April 22, 2008
Topics: 2008 , Barack Obama , cbs , cnn , Exit Polls , Gary Langer , Hillary Clinton , Mark Lindeman , msnbc , National Journal , SurveyUSA
I will be live-blogging here starting very soon on what the exit polls will have to tell us about the exit polls. More details to follow, but please feel free to use this as an open-thread on what is appearing on the net and elsewhere on the exit polls. Here are the links where official exit poll tabulations will appear shortly after the polls close at 8:00 p.m.:
Comments will appear in reverse chronological order.
11:25 - Folks, I'm calling it a night. With 88% of the vote counted as of this writing, Clinton is holding a lead of exactly 10 percentage points. The pre-election polls did reasonably well, especially given that Clinton did better among those deciding late. The early leaked exit poll estimates were off once again. More tomorrow.
9:50 - Reader "Anon" posted the link to the Pennsylvania Secretary of State's official count. At this point, the official count is probably the best source of information about the ultimate vote count. Though having posted that link, I now see that the percentage of the vote counted in the official network news sites.
9:45 - After nearly 90 minutes, the exit poll tabulations update, and Mark Lindeman reports the underlying estimate extrapolates to 54% Clinton, 46% Obama. The geostrata show Philadelphia at 18% of all voters, Philly suburbs at 16%.
8:57 - Noticed an error in the 2006 turnout numbers I posted below. Now corrected.
8:50 - NBC calls Pennsylvania for Clinton.
8:37 - Here are some of the most important numbers to watch in the exit poll tabulations as they update: The 52% to 48% Clinton lead assumes that Philadelphia County is contributing 16% of the statewide vote and the rest of the Philadelphia suburbs (Berks, Chester, Delaware and Montgomery Counties) is contributing 16%.
These "geostrata" estimates are one of the most important aspects of the early tabulations to update as the evening wears on as the analysts incorporate, first hard turnout counts from the sampled precincts, and later the actual vote count.
For comparison's sake, here are some comparable actual numbers. As of January, the Democrats of Philadelphia County were 19% of all registered voters statewide, but in the 2000 Senate primary they contributed 16.7% of the vote. In the 2002 gubernatorial primary between Ed Rendell and Bob Casey, Philadelphia surged to 23.0% of votes cast and in the 2006 primary for Lieutenant Governor it was only 11.1%
still 22.7% of the votes.
The Democrats in the four counties that the exit pollsters define as Philadelphia suburbs were 15.6% of registered Democrats statewide in January. In the three contests cited above, the Philly suburbs contributed 9% in 2000, 16.2% in 2002, and 10.7%
21.6% in 2006.
PS: Nearly forgot, for those not noticing the fine print, is that these two regions are, as expected, Obama's best in the state. So if the composition ends up looking more like 2002
and 2006 than 2000 or 2006, his numbers will improve
Also, I should note that those numbers come from a spreadsheet shared by friend -- It is always possible I've made a computation error, so if anything looks out of order, please let me know.
8:17 - The tabulations show Clinton doing 10 points better among those who made up their minds in the last 3 days (she leads 60% to 40%) than among those who decided earlier that that (divide 50-50%). That is as good or better in terms of late deciders than in previous contests. See the 6:26 update.
8:01 - The characterization from MSNBC is "too close to call." Their website has the initial cross-tabulations posted, and Mark Lindeman has his extrapolation for us: 52% Clinton, 48% Obama. These are based on interviews received just before the polls close.
See the 6:39 update, but it's worth remembering that this initial update is almost always based on what exit pollsters call the "composite" estimate (an average of the exit poll tallies and pre-election polls. Subsequent updates will add in more exit poll interviews being phoned in now, constantly improving estimates of the turnout by the exit poll "geostrata" and, gradually actual vote for the sampled precincts. Also very important to keep in mind: The as-the-polls-close estimate for Ohio also had Clinton leading by four points.
7:48 -- I'm back.
Alert reader Daniel T posts the link to an AP write-up of some of the none vote preference results from the preliminary exit poll tabulations. With the same caveats as noted below about late afternoon partial results, here is some initial demographic information:
As expected, Pennsylvania's Democratic voters were overwhelmingly white and — as usual in Democratic contests — there were more women than men. About three in 10 were age 65 or over. Nearly half were from families that earned less than $50,000 last year. A quarter had household income of more than $100,000 and about as many reported having a postgraduate degree.
Three in 10 Pennsylvania Democratic voters were union members or had one in their household. And four in 10 had a gun owner in the household.
Those numbers are more or less in range with what pre-election polls reported, although the $100K number is higher. For what it's worth: telephone polls get higher refusals on income (for reasons that ought to be obvious).
Those clicking back through to my post on demographics will note that SurveyUSA reported a much higher percentage of college educated voters than other polls. That is almost certainly a function (as learned this afternoon via email) of the very different question they ask about education:
Have you graduated from a 4-year college?
Yes, press 1.
Most telephone surveys use a multi-category question that asks about years of education and typically offers the category of "some college" (meaning coursework sort of a degree). As such, the difference for SurveyUSA was almost certainly about the question, not about their sample
7:00 - This is probably a good time to remember these words of wisdom from TNR's Mike Crowley, written at this time on March 4:
Stop the Madness!
In the last couple of hours I've gotten allegedly reliable Ohio exit poll information showing
a) Narrow Obama lead
b) Narrow Hillary lead
c) Hillary blowout
I think from now on political journalists should turn off their BlackBerries from 5-8pm on election nights and, like, go do ESL tutoring or some other charitable work instead.
In that spirit, I am going to use the next 30 minutes to relocate to the Pollster.com "home office." I'll be back online before the polls close.
6:49 - Josh B comments:
cnn is reporting that according two their exits 58% of those that decided in the last week went for clinton how does that compare to your chart i am not to good at interpreting charts.
The ultimate is how that number -- if accurate -- compares to those who decided earlier. The table shows that the comparable number for Ohio was 57% (and that was from the final exit poll, weighted to match the result).
6:39 - Shortly after the polls close at 8:00 p.m., our friend Mark Lindeman will report the extrapolated overall vote estimate used to weight the exit poll cross-tabulations. These estimates begin as a mashup of pre-election polls and the interviews exit polls conducted at polling places and over the phone (with early voters) by the networks. These estimates improve, becoming more accurate over the course of the night. Click here for the usual caveats on how these numbers are derived and how they improve over the course of the evening. And see my post 3/4 National Journal column for the evidence that while the "as the polls close" numbers are better than those leaking now, they have still had their problems.
6:26 - I have my television tuned to MSNBC, where Nora O'Donnell occasionally pops up and reads preliminary exit poll results that do not pertain (directly) to vote preference estimates. One result she teased just before 6:00 involved the percentage (17%) that said they made up their minds in the last three days. I spent some time gathering results on that question from primaries held since 2/5 this afternoon, and here they are:
The first four columns of numbers in the table above show the percentage clinton received among each subgroup, those who decided in the last three days or before, and those who decided in the last week or before. The last two columns show the percentage that decided "today" (on Election Day) or over the "last three days" before that. Given the numbers in the table, the 17% number O'Donnell cited is consistent with the previous primaries.
What stands out from the table (as Gary Langer noted in his column yesterday) is the consistent and often large advantage that Hillary Clinton has had with late deciders [as compared to those who decided earlier -- thanks RS] in all of the contests since Louisiana. The key question is how the results we will have at 8:00 will compare.
Caveat emptor: I gathered the data for the table quickly. Errors are possible.
6:05 - Just to put a bit more emphasis on the previous update: The results "leaked" for Ohio at this hour on 3/4 showed Obama leading by 2. Clinton won by 10.
6:00 p.m. - I see that at least one publication has posted leaked exit poll results that most will consider a bit surprising. Please keep in mind that these leaked estimates have typically shown a skew in Obama's favor. See the table in my 3/7 National Journal column. Errors on the margin occurred (at this hour) in Obama's favor in 18 or 20 states I looked at, averaging 7 points in Obama's favor. The numbers leaked previously at this hour hit double digits in OH, RI, VT, NJ, MA, GA and AZ.