Model moves toward the Democrat in Arkansas' 2nd District

Our forecast in Arkansas' 2nd Congressional District moved 12.3 points toward the Democrat over four days. On August 16 our model gave the Democrat a 21% chance; as of August 20 it gives the Democrat a 34 in 100 chance, with the Republican at 66%.

The expected margin moved with it. Our model now puts the mean result at R+4.3, against R+8.4 in the earlier run. The spread remains wide: our 5th-to-95th-percentile range runs from R+21.4 to D+12.4, which covers comfortable outcomes for either side.

One poll of the district appears in the payload. Hendrix College surveyed 1,112 likely voters on August 12 and 13 and found the Democrat at 48% and the Republican at 44%. That result predates the August 16 run by three days, so the movement since then is not explained by new district polling in this payload. The model moved; the cause is not something we can pin down from what is in front of us. It may reflect our national inputs, where our average of 25 generic-ballot polls over the last 45 days stands at D+6.7.

Nationally, our model gives Democrats a 94% chance of winning House control, with a mean of 242.6 seats against the 218 needed. One caution on that figure is ours to own: our simulation draws error at the national, census-division, state and district levels, but not across demographically similar districts in different places, because we have no cluster data for it. That omission makes the House control number marginally firmer than a fuller treatment would leave it. We are not putting a size on the gap, because this run does not measure one.