The DeSart model released an updated prediction of the election outcome. The model expects that Clinton will achieve 49.5% of the two-party vote share in Virginia, whereas Trump will end up with 50.5%. In comparison, on August 7, Clinton was predicted to end up with 50.5% of the vote.
Historically, Virginia has been a purple state, in which neither the Democrats nor the Republicans have had overwhelming support to clinch its electoral college votes. Hence, predictions here are of particular importance.
Putting the results in context
As any other method, econometric models are subject to bias. In general, a good strategy is to not be overly confident the results of a single econometric model. Rather, one should examine how a econometric model's results compare to benchmark forecasts.
Comparison to other econometric models
An average of recent econometric models in Virginia sees Trump at 53.1% of the two-party vote. Relative to his numbers in the DeSart model Trump's econometric model average is 2.6 percentage points better.
The DeSart model in comparison with PollyVote's prediction
The results of the DeSart model for Trump are thus 0.7 percentage points above the combined PollyVote, which at the moment predicts a value of 49.8% in Virginia. In comparison, a look at the PollyVote national prediction for Trump shows that the actual results are 3.2 percentage points higher.