Ric Fernholz writes:

I wanted to tell you about a new website I built together with my brother Dan. The 2020 Election Scenario Explorer allows you to explore how electoral outcomes in individual states influence the national election outlook using data from your election model.

The map and tables on our site reveal some interesting observations about the election and your model. The site provides a measure of the influence of different states using the expected reduction in entropy or variance, following the data generated by your model. Several of the most influential states according to this measure differ from those states emphasized by more common “tipping point” analyses.

I appreciate you sharing your code and simulation output with the public, as this made our project possible.

Open data and code ftw!

**P.S.** They should round those numbers to the nearest percentage point (see section 2.1 of this article).

I don’t understand what you mean by “the expected reduction in entropy or variance”. What would be the cause of a reduction in variance?

“Scenario Probability: 100.00%”

Wow, glad we have the completely certain outcome of the election determined. I’m also glad they included the two decimal places. If they had just said “100%”, I would have been worried it only had a probability of 99.51% and they rounded up. To avoid confusion, I always encourage people to include as many decimal places as possible when reporting percentages.

Adede:

Next time, please read to the end of the post. I made the exact point you made in my P.S.

Not directly on topic but:

After all the pollster bruises in 2016 everyone’s biasing their models a bit more toward Trump just in case. It doesn’t seem to have occurred to anyone that just the opposite might happen and Biden will win in a massive landslide.

Jim:

I disagree that “everyone’s biasing their models a bit more toward Trump.” I think people are adding uncertainty to their model, not bias.