A partisan poll puts TN-9 within four points; our model does not move

One new survey landed in Tennessee's 9th District. Hart Research Associates, polling 400 likely voters for Tennessee Rise PAC and Three Star PAC between September 1 and September 3, put Republican Brent Taylor at 48 percent and Democrat Justin J. Pearson at 44 percent. The poll does not report a margin of error, and a four-point gap in a sample that size is a narrow one.

Our forecast did not move. The model gives Pearson a 100 in 100 chance in TN-9, with a mean margin of D+54.5 and a 5th-to-95th percentile range of D+38.9 to D+69.9. The run before this one, at 10:32 AM ET on September 10, had the same probability and the same mean margin, with a top-end range of D+70.1. That is the whole of the change.

The distance between the poll and the model is the story here, and it is large: the survey's numbers sit roughly 50 points from our central estimate and well outside the range the model treats as plausible even at its Republican-leaning tail. Our forecast weighs a single sponsored poll of 400 respondents against everything else it knows about the district, and in this case the poll did not shift the estimate at all.

Nationally, our average of 24 generic-ballot polls over the past 45 days stands at D+6.3. The model gives Democrats a 94 percent chance of winning House control, with a mean of 239.4 seats against the 218 needed. One caveat on that figure is ours to make: our simulation correlates 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 number is marginally firmer than it should be.