Our AZ-2 forecast moves eight points toward Nez, to even

Our forecast in Arizona's 2nd District has moved toward the Democrat. As of our September 4 run, the model gives Jonathan Nez a 50 in 100 chance against Republican incumbent Eli Crane. Our run on August 28 put the figure at 42%. That is a move of 8.1 points of Democratic win probability over seven days.

The underlying margin moved with it. Our mean margin is now R+0.1, from R+2.1 a week ago. The spread narrowed slightly as well: our 5th-to-95th percentile range runs from R+16.1 to D+15.9, against R+18.6 to D+14.4 in the earlier run. On those numbers the district is a coin flip, and the range makes clear how much room remains on both sides.

The payload does not show new district polling arriving in that window. The most recent survey we hold is a GBAO poll of 500 likely voters in AZ-2, fielded August 21-24, which had Crane at 46% and Nez at 44% — a close result. It finished fielding before our August 28 run. The earlier GBAO poll of 500 likely voters, fielded June 11-15, had Crane at 44%, Nez at 41% and 7% for others. So the movement here is the model's, and we are not going to attach a cause to it that the data do not support. National conditions are one candidate: our generic ballot average, drawn from 25 polls over a 45-day window, stands at D+6.3.

For the chamber, our model gives Democrats a 93% chance of winning a House majority, with a mean of 239.4 seats against the 218 needed. One caveat is ours to own: our simulation correlates error nationally, by census division, by state and by district, but we have no cluster data to correlate demographically similar districts across regions. That makes the House control number marginally firmer than a fuller model would leave it.