Second St. Anselm poll in NH-2 leaves our numbers where they were

Two St. Anselm surveys of New Hampshire's 2nd District now sit in our average. The more recent, fielded August 17-18 among 701 likely voters, had the Democrat at 50 percent and the Republican at 35. The older one, fielded March 16-18 among 739 registered voters, had the Democrat at 48 and the Republican at 36.

Our model gives the Democrat a 94 in 100 chance in the district, with a mean margin of D+15.0. Before this run it was 94 percent and D+15.3. The 5th-to-95th percentile range runs from R+1.2 to D+31.4, essentially where it was at the prior run, which put it at R+1.0 to D+31.4. Nothing in the polling changed the shape of the race as our model sees it; the March survey is five months old and points in the same direction as the August one, at a slightly narrower margin.

The wide lower tail is worth noting. Even at a mean of D+15, our simulation leaves about a 6 percent chance the Republican wins, and the 5th percentile outcome is a narrow Republican win. That reflects error drawn at the national, division, state and district levels rather than any specific signal in these two polls.

Nationally, our average of 28 generic-ballot polls over the past 45 days stands at D+6.5. Our model gives Democrats a 93 percent chance of a House majority, with a mean of 240.1 seats against the 218 needed. One caveat is ours: our error model correlates districts by geography but not by demographic similarity, because we have no cluster data for that term. That makes the House control number marginally firmer than a fuller decomposition would leave it. In the Senate, we have Democratic control at 49 percent and Republican control at 50 percent.