In short, those fancy models that show probability of victory are only as good as their ingredients, and if the polls are wrong, the poll aggregations will be wrong as well.
In an important article, Huffington Post shows four ways polls can be wrong. And all four ways end up with numbers more favorable to Republicans than they should be. I won't repeat the content of the article here. However, the information is likely to misrepresent several current races, all currently within a few percentage points.
So much for a calculated, mathematical model for trying to predict the outcome of an election.
(Thanks to Sam Wang for the link to this article.)
Polls Have Likely Hidden Errors
Kudos to Sam Wang for linking to an article which proves he may be wrong.
In an important article, Huffington Post shows four ways polls can be wrong. And all four ways end up with numbers more favorable to Republicans than they should be. I won't repeat the content of the article here. However, the information is likely to misrepresent several current races, all currently within a few percentage points.
So much for a calculated, mathematical model for trying to predict the outcome of an election.
(Thanks to Sam Wang for the link to this article.)
Polls Have Likely Hidden Errors
Kudos to Sam Wang for linking to an article which proves he may be wrong.
No comments:
Post a Comment