Just wanted to drop a note saying even if I don't have something specific to write about, I'm here updating the numbers on at least a daily basis. There's been a lot of faux-news the last few days. There have been things for pundits to yell about (aren't there always) but nothing to significantly move the model.
Both the Electoral Map and the National Summary have conveniently located "last updated...." fields if you're ever wondering how current the numbers are.
I have a question about how your model turns the polling leads into probability of winning that state.ReplyDelete
1) WA has Obama +14.6 and a probability of winning of 100%, LA and MS have Romney +15.0 but a probability of winning of 99%.
2) WI has Obama +5.4 with 89% probability of winning, but AZ has Romney +5.4 with 87% probability of winning.
What accounts for these differences?
Wow, great questions both of these. I thought hard about each while designing the model.Delete
There are two effects in play here, other than polling lead, which affect a candidate's chances of winning a state.
The first is the national polling. National polling informs the state polling then state outcomes inform the simulated national outcome. There's not a great state-pair example at the moment but all things being equal the model has Romney with a small national lead and will take a slightly more optimistic view of a lead by Romney than of a similar one by Obama.
The second is sample size. Your WA vs. LA/MS and WI vs. AZ chiefly driven by this effect.
OR and WI are also a great example. Polling in OR has been sparse; polling in WI has been extensive. As a result the model is more confident in the WI average than the OR average, so much so that the model is more confident in Romney's chances in WI than in OR.
I believe I am not understanding the statistics behind the "most likely winning EV total". I assume this means E [ EV | Obama wins ].
To get to the answer in your model (332), Obama has to win VA, CO and FL. For this to be the most likely winning EV total, it would have to be the case that among the following events:
1. Obama wins VA, CO, FL
2. Obama wins 1 or 2 of these states
3. Obama wins none of these states (i.e., OH decides it)
Event #1 is the most likely.
But using the probabilities in your model,
P(VA, CO, FL) = 0.172592
P(VA, CO, not FL) = 0.202608
Doesn't that make 303 more likely than 332 (i.e., FL in the Romney column)?
Typo in my post immediately above...ReplyDelete
I didn't mean E [ EV | Obama wins ]
I meant Max Likelihood [ EV | Obama wins ]