Most Vulnerable House Seats, Revisited

Based on a recent critique from Nate Silver, I have decided to conduct a seat-by-seat analysis of the U.S. House. In the tables below, I assign probabilities of Republican gains in the 88 most vulnerable Democratic seats. I also list probabilities of Democratic gains in the 10 most vulnerable Republican seats.

As the reader may notice, the Republicans have a much greater than 65 percent probability--the estimate that Nate Silver asserts--of winning the House. The Democrats are likely to win four or five Republican seats. However, the Republicans have at least a 92 percent probability of winning each of 31 Democratic seats. They have at least a 50 percent probability of winning each of the next 24 most vulnerable seats. They even have over a 10 percent probability of winning each of the 56th through 75th most vulnerable seats. This analysis implies that the Republicans are expected gain approximately 31 + 1/2*44 = 53 seats and lose about five seats. Thus, the Republicans are poised to net about 48 seats, while they only need to gain 39 seats to take control of the House.

What's the probability the the Republicans could only gain 38 or fewer seats? Using a back-of-envelope calculation, I would say that the Democrats only have about a two percent chance of retaining the House. Now, I am assuming independence between the individual seats and zero uncertainty in my seat-specific probability estimates. So, in reality, the Democrats may have as much as a 10 to 15 percent chance of retaining the House (coincidentally, my analysis on the generic ballot question yields about this probability). However, I do not think that the Democrats have anywhere near one-in-three odds of maintaining the majority.


Competitive Democratic Seats


Competitive Republican Seats

SENATE UPDATE: Despite DE, Republicans Still Predicted to Gain Six Seats

Using a similar methodology as my model for the U.S. House, I predict that the Republicans will gain six seats in the U.S. Senate. Here is a seat-by-seat summary (margin of victory in parentheses; party turnover in italics):

Safe Democratic, 7 Seats (15 percent+) :
CT (Dodd)
Inouye (HI)
Mikulski (MD)
Schumer (NY-A)
Gillibrand (NY-B)
Wyden (OR)
Leahy (VT)

Strong Democratic, 4 Seats (5.0 -15.0 percent):
Boxer (CA)
DE (Kaufman)
IL (Burris)
Murray (WA)

Weak Democratic, 2 Seats (0.0 - 5.0 percent):
Reid (NV)
WV (Byrd)

Weak Republican, 4 Seats (0.0 - 5.0 percent):
Bennet (CO)
NH (Gregg)
PA (Spector)
Feingold (WI)

Strong Republican 4 Seats (5.0 - 15 percent):
FL (LeMieux)
Grassley (IA)
OH (Voinovich)
MO (Bond)

Safe Republican 16 Seats (15.0 percent+):
AK (Murkowski)
Shelby (AL)
McCain (AZ)
Lincoln (AR)
Crapo (ID)
IN (Bayh)
Isakson (GA)
KS (Brownback)
KY (Bunning)
Vitter (LA)
ND (Dorgan)
Burr (NC)
Coburn (OK)
DeMint (SC)
Thune (SD)
UT (Bennett)

Most Vulnerable House Seats

Now that Nate Silver has come out with his own seat-by-seat house projection, I have decided to publish my list of most vulnerable Democratic and Republican seats. My methodology is not very sophisticated and I do not assign probabilities to whether a given seat switches party. However, this list should provide the reader an idea of which seats will be the first to switch from Democratic to Republican.

My ranking of the most vulnerable seats is essentially based on the 2008 presidential vote, demographic composition, and ideological orientation of each district. A Partisan Index score of under 30.0 should be interpreted as a solidly Republican district, while a score of over 70.0 indicates that the district is solidly Democratic. Districts between 30.0 and 45.0 are Republican leaning and districts between 55.0 and 70.0 are Democratic leaning. Districts in the 45.0 to 55.0 range indicate marginal status.

I list the one hundred most vulnerable Democratic seats and the twenty-five most vulnerable Republican seats. Open seats are in bold.

HOUSE UPDATE: Republicans Remain in Position to Take Majority

Based on polling data released over the last eight months, Republicans are expected to gain between 35 and 60 seats in the U.S. House of Representatives (with a 90 percent level of credibility). According to the model, the most likely outcome is about a 48 seat gain by Republicans, unchanged from the previous estimate. If the polling holds steady, Republicans seem to be poised to retake control of the U.S. House of Representatives with the largest electoral landslide since 1994. In fact, based on a Monte Carlo simulation, the Republicans have an 85 percent probability of retaking the House.

A statistical model that analyzes the results of 15 independent polling firms indicates that Republicans lead Democrats by a margin of 2.0 percent on the so-called generic ballot--a measure of national voter preference between the two major congressional caucuses. This figure is slightly greater than the July estimate of 1.9 percent. The August estimate implies that, if the election were held today, Republicans would achieve approximately a 19 seat majority over the Democrats--a modest, but decisive advantage.

Over the next three months, I will update this model and estimate Republican electoral gains. The charts below will provide the change in voter preferences over time, along with the probability distribution of the number of seats gained by Republicans on election day. See my April 30, 2010 post for an explanation of my methodology.