Maine's 1st District poll trims our margin, not our odds

A University of New Hampshire survey of 657 likely voters in Maine's 1st District, fielded September 17-21, has Democratic incumbent Chellie Pingree at 57 percent and Republican Ronald Russell at 35 percent. That is a 22-point lead.

Our model still gives Pingree a 100 in 100 chance of winning the seat. The new number did move the expected margin: our mean is now D+29.8, down from D+33.2 in the run earlier this afternoon, with a 5th-to-95th percentile range of D+15.2 to D+44.4, previously D+18.5 to D+47.8. The poll landed a few points under where our average had the race, so it pulled the central estimate toward itself without changing the probability, which was already at the ceiling.

The district sits well outside the set of seats that decide chamber control. Nationally, our generic-ballot average is D+8.3 across 30 polls over the past 45 days. Our model gives Democrats a 98 percent chance of winning a House majority, against 2 percent for Republicans, with a mean of 245.7 Democratic seats and 218 needed for control. One caveat on that figure is ours to own: our simulation draws correlated error at the national, census-division, state and district levels, but it has no term linking demographically similar districts in different places, because we have no cluster data to build one. That omission makes the House control probability marginally firmer than a fuller model would report.

The Senate is the closer question. Our model gives Democrats a 53 in 100 chance of winning Senate control and Republicans 46 percent, with a mean of 50.6 Democratic seats. Democrats need 51 seats; Republicans need 50, because the vice president is a Republican and a 50-50 tie goes to them. Nothing in the Maine poll speaks to that.