GBAO poll finds AZ-2 close as our forecast settles at even

A GBAO survey of 500 likely voters in Arizona's 2nd District, fielded August 21-24 and reported by Politico, put Republican Eli Crane at 46 percent and Democrat Jonathan Nez at 44 percent. Two points on a sample that size is not a measurable advantage for either candidate. The reading is a close race.

Our model now gives Nez a 50 in 100 chance and Crane 50 percent, with a mean margin of even and a 5th-to-95th percentile range running from R+16.0 to D+16.2. That is unchanged from our previous run this morning, which also had the district at 50-50 with a mean margin of even and a range of R+16.1 to D+16.0. The new number is a change from where this site left the race on August 27, when our model had moved toward Crane and put Nez at 42 percent. The district has since come back to a coin flip.

The practical content of the GBAO poll, then, is confirmation rather than movement. It is consistent with a district our model already treats as genuinely even, and the width of our range — roughly 16 points of margin in either direction — is a reminder that a single 500-voter poll does little to narrow the plausible outcomes here.

Nationally, our average of 26 generic-ballot polls over the past 45 days stands at D+6.5. Our model gives Democrats a 93 percent chance of winning House control, with a mean of 240.0 seats against the 218 needed. One caution on that figure is ours to make: our simulation draws error nationally, by census division, by state and by district, but we have no data to correlate demographically similar districts across state lines. Without that term, the House control probability is marginally firmer than a fuller accounting would leave it.