Um, poll Twitter. State errors may be correlated. More interesting Q: can we model a rare event based only on 11 previous cases—as 538 does?
-
-
Replying to @zeynep
I'd rather discuss the philosophical underpinnings of running 20K simulations of a rare event & taking output distribution as probabilities.
7 replies 4 retweets 36 likes -
Replying to @zeynep
Doesn't any model that yields probabilities have to model those rare events (to understand polling error prob. for calibration)?
2 replies 0 retweets 1 like -
Replying to @HerbieLewis
.
@HerbieLewis There is a bigger question here: can you model very very rare events based on very very few cases, aka what 538 does?5 replies 0 retweets 8 likes -
Replying to @zeynep @HerbieLewis
What does 'very few cases' mean? They have thousands of polls across 1000s of elections, depending on defn. of election
1 reply 0 retweets 1 like -
Replying to @DinoStraciatela
.
@DinoStraciatela@HerbieLewis 538 model is based on 11 previous presidential elections. That's it. It's a tough thing to model rare events.3 replies 0 retweets 11 likes
Important point, partic b/c outcome is binary. OTOH strong causal mechanism helps.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.