Except the models were off by a lot, plus what were all the results from these models used for? To provide a probability of a candidate winning the election. Again, don't see why you can't accept the assumptions in his midels did not properly account for essential variables, hence making it a bad model.The model is based on models similarly developed for sports betting. When a team wins against the bookmakers odds, you don't say that they don't know anything about football. You just realize that on any given Sunday, shit happens.
- 1