|
heavyblinker -> RE: Why the polls were wrong (3/13/2017 6:02:30 AM)
|
quote:
ORIGINAL: Musicmystery
That's actually the point right there -- the media's interpretation vs. what the polls actually showed giving the statistical margin of error.
All kinds of crazy predictive models were drawn based on nothing but a poor understanding of statistics, then reported as fact.
In the article it says that the problem was that the media drew on opinion polling more than conversation polling. It has nothing to do with the interpretation of the data, it's about the nature of the data. That's why a polling company that has nothing to do with politics was able to 'predict' the outcome.
Sort of like how BoscoX says he's not a fascist then turns around and supports fascist policies. If you took him at his word, you wouldn't be able to figure out who he really is. But if you look at the threads he posts and the things he says in exchanges, you will see the truth.
quote:
Our conversation data also raise a different, but fundamental, question about the predictive power of public opinion data in predicting behavior, at least given the unique features of a campaign that featured two unpopular candidates, non-traditional campaigning, and a late October surprise.
It seems Hillary was winning up until the very last minute. So the polls generally work well, but failed because of the specific conditions of this election.
Of course, now because of this horrible surprise, idiots like Bosco assume that it's all because Alex Jones knows more about elections than professional pollsters and the media.
|
|
|
|
