Articles and Analysis


Handicapping the House: Part II

Topics: 2006 , Slate Scorecard , The 2006 Race

Yesterday, our Slate update shifted to a district-by-district focus on races for the U.S. House. Our initial tally shows Democrats right on the edge of statistically meaningful leads in enough districts to take control of the House, and Democratic challengers running within the margin of error in many more. While we are working to creating a more comprehensive scorecard, I want to say a bit more about how our initial count given the limitations of the data.

For now we are focusing on non-partisan surveys conducted since late August (which allows inclusion of the first wave of Majority Watch surveys conducted August 27-29). We have excluded the surveys sponsored by campaigns or the party committees (including those conducted by my firm).

Looking at the survey averages in districts with two or more polls available, we see Democrats leading beyond the margin of error in ten districts currently held by Republicans (the number of surveys analyzed is included in parentheses):

In addition, we see statistically significant Democratic leads in four more districts held by Republicans surveyed only once by non-partisans since the summer (all four were polled by the Majority Watch project):

[Note: We inadvertently omitted Ohio-18 and North Carolina-08 from last night's initial Slate update].

Perhaps more troubling for Republicans is that we see no Republican leading in any district currently held by a Democrat. Moreover, of the 23 Republican held seats currently rated as "toss-ups" by the Cook Political Report, Democrats lead by significant margins in 9, Republicans leading in none just one (Minnesota-02).** The remaining 13 Republican "toss-up" seats look too close to call based on available data. And that says nothing of the 31 Republican seats that Cook rates at "lean" or "likely" Republican, where public polling is scarcer still.

Of course, readers should remember the limitations of these data. Any one poll can produce an odd or contradictory result and many of the polls conducted in September may already be stale. Consider, for example, Iowa's 1st District (an open seat currently held by Republican Jim Nussle). A Majority Watch poll in late August showed the Democratic candidate Bruce Braley leading Republican Mike Whalen by thirteen points (54% to 41%). Two weeks later, a DeMoines Register/Selzer poll conducted two weeks later had Braley ahead by seven (44% to 37%). Then a Zogby poll at the end of September showed Braley trailing by thirteen (34% to 47%). And finally, a poll conducted by my firm last week for the Democratic Congressional Campaign Committee had Braley ahead by 10 (48% to 37%). So over the course of six weeks, polls in one district show everything from a 13 point Democratic lead to a 13 point deficit with undecided percentages ranging from 5% to 19%. These differences are far beyond sampling error and almost certainly the result of differences in pollster methodology. And that's just one district.

Again, we are working on creating a House summary scorecard for Pollster.com, but it will be limited by both the relatively small number of public polls and their inevitable conflicts.

**Correction: I wrongly included MN-02 (rather than MN-06) among the list of seats rated a "toss-up" by the Cook Political Report. Four polls in MN-06 since mid-September give Democrat-Farm-Labor candidate Patty Wetterling an average lead of one percentage point (45.7% to 44.7%) over Republican Michelle Bachman. Apologies for the error.


Tony v:

Hey! Don't harsh the Braley campaign (who I've never heard of before this post). It sounds like there were three polls showing him ahead by 7 to 14 points, a reasonable spread, and fracking Zogby as a huge outlier with a 13 point deficit.

This would be far from the first time that Zogby was a significant outlier, and this really doesn't tell us much about the reliability of other polls in general.


The Professor:

It was a zogby phone poll not his internet stuff which is where he is really off. That said it was a very strange result given the other polls he released that day. However, the tv commericials on at that time were 3 to 1 anti-brayley. The Republicans bought into the poll as they poured a lot of new money (almost a half million) in to tv ads buys in Iowa's 1st district last week in a hope of keeping the seat red.


Something that troubles me: most of your House guesses are based on RTS/Majority Watch. If RTS is reliable, no problem.

But I have one reason to be concerned about RTS: when I look at the seats where RTS polled in both August and October, I generally see no big trend to the Democrats.

So if the other seats polled are also where they were in August, the Republicans would be doing much better in RTS polls than they are (since I don't get the impression that this many Republicans were in trouble in August). It follows that either:

a) the seats where RTS polled in both August and October are outliers (seats where the Reps have held on) or

b) Maybe the Dems aren't doing as well as RTS thinks, and the Democratic leads are based on screwed-up samples or something, or

c) the Republicans were a lot weaker in August than the national media thought.

Any thoughts from anyone?


Anonymous Jim:

I don't have the competence in statistics but I was wondering if it would be possible to generate a composite statistic which would express the likelihood that one party wins a majority of house seats (and a corresponding expression of the confidence one could have in that statistic). Presumably, one could look at how good that composite statistic did in predicting prior house elections. Is there such a statistic?


NC-08 I see the poll by public opinion strategies for NC-08 here and at one other site, but I cant seem to find anywhere that has info on what the sample looked like. For one poll to show Larry Kissell up by 7 and another to show him down by 16 is very very odd.


Gary Kilbride:

NV-2 is strangely missing from the list. It is a huge primarily rural district that encompasses nearly the entire state other than Las Vegas. A Democrat has never won the district, which has a +48,000 GOP registration edge, but Jill Derby is extremely competitive this year. There are at least two polls that fit the criteria, late August or later and from a neutral firm. Mason-Dixon gave Dean Heller a 45-42 lead over Derby while the Reno-Gazette had it 45-37, also in favor of Heller.




Bill :

I understand why Texas-22 is missing from your lists of polled districts, but shouldn't it be included in any summary total of likely Dem gains?


Tony v:

Bill: TX-22 is traditionally not even polled, and is just accepted a Democratic give-me. In fact, it would be very different to poll. "Do you plan on voting for Democrat Nick Lampson, or do you plan to vote for a write in? Tell us who please."

The Professor: Zogby's internet ones are completely crazy, but his phone polls aren't reliable either. They are very often outliers. And really, do do you trust the scientfic credibility of a man who does the internet ones, anywhere else?



What do you think about FL-09?



The result by SUSA in the Reynolds district strike me as odd...too big a turnaround.

So I look at the fine print at their site, and it informs us that a substantial number of phones(in Erie county) were down due to the snowstorm, and they plan a new poll to double-check.

Read the fine print!



I don't think much of the Majority Report polls. These are robocalls. In the race in which I am working we had one MR poll in August and another just this week which both showed our Dem candidate with just a 3 percent lead. Our own polls and now one from the major newspaper, show us with 16 and 19 percent leads respectively. The RNC apparently believes the MR polls, however, as they just dumped 1.1Million into our opponent's race and have booked 100 hotel rooms in our district for out of town workers.


Post a comment

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.