Weird 538 maps

[Gustaf]

Yeah the biggest problem with the model right now is that it has fat tails (which yeah okay, still some uncertainty because we're months from election day, guess that makes sense) that aren't correlated with each other at all. That's why you're getting obviously bunk outcomes like R-AZ but D-LA.

I'm not sure why Nate's model is doing this because I've definitely seen him harping on state correlations before. Right now the model seems to just grab tail-outcomes for random states in random directions and it leads to obviously whacky stuff.

With that said I spotted this gem on the back panel a few days ago

The issue is that they're allowing a lot of subgroup variance. If you think about it you can tell how many of the weird maps happen.

It can be, say, "extremely good Biden black voter scenario" (black turnout 80% or something) combined with "extremely good Trump Hispanic voter scenario" (Trump wins Hispanics!) and then suddenly Biden is winning places in the Deep South with all his black voters while Trump wins New Mexico, etc.

One of the specifically weird things is that they allow Corona to be a group thing for states. So when you combine a bunch of different tail end scenarios for different groupings, including some that group states along non-political lines (like Corona) you get these really wild outcomes.

[Gustaf]

The issue is that they're allowing a lot of subgroup variance. If you think about it you can tell how many of the weird maps happen.

It can be, say, "extremely good Biden black voter scenario" (black turnout 80% or something) combined with "extremely good Trump Hispanic voter scenario" (Trump wins Hispanics!) and then suddenly Biden is winning places in the Deep South with all his black voters while Trump wins New Mexico, etc.

Right, but my point is, in an era as polarized as this one it's pretty unlikely to simultaneously see contrasting trends like that. These trends are generally going to go in the same direction. The subgroup variance needs much more covariance. You'd really only build a model which does this frequently if 2016 realignment takes melted your brain.

One of the specifically weird things is that they allow Corona to be a group thing for states. So when you combine a bunch of different tail end scenarios for different groupings, including some that group states along non-political lines (like Corona) you get these really wild outcomes.

This is interesting - didn't know about this.

Is that a Jorgensen win in WY or did Wyoming literally just disappear?

It's a weird aesthetically non-intuitive way of highlighting only the states of the winner - Trump wins WY here.

I'm not really disagreeing with the bolded part, just noting that this is the underlying thing in the model which causes these weird maps.

[Gustaf]

Oregon is one of the states least affected by Covid - they're 7th least per capita covid deaths. So that may be part of it.

[Gustaf]

Not exactly a map, but I find it bizarre the model still gives Trump a 28% chance of winning a Clinton state. This means they think there is at least a 15% chance Trump wins a Clinton state and still loses the electoral college. That strikes me as very very unlikely.