Putting up hypotheses based on data and testing them isn't "wrong".
Since polls are generally very unreliable in primaries compared to general elections, trying to put in more data makes sense.
But I guess joining the latest lynch mob to shout in unison is more fun for some people.
Well, he has seemed awfully certain about this, showing little indications of considering arguments that ran counter to his conclusions (and making a lot of dubious arguments himself, such as the idea that Trump as a candidate was more or less equivalent to earlier "anti-establishment candidate" (none of whom shared Trump's level of support over time, his celebrity status, and probably lots of other factors). Now that Silver is starting to backtrack, at the very last moment, I hardly think he should be considered the victim of a "lynch mob".
And on the flipside, when he's right he is largely lauded as a genius, even when his statistical modeling barely differs from a simple polling average.
Those are different points. I agree Silver has seemed reluctant to admit Trump is doing well.
What I take issue with is the constant ridicule of him not just looking at polling data. I find that line of attack pretty silly.
I also think it's generally petty to hate on people because other people laud them as geniuses. I guess the saintly users on Atlas Forum would have refused lucrative contracts with the media out of principle but I harbour no such self-illusions. If people proclaimed me the Messiah for pointing out obvious things I'd cash that check.
It's not that he's not just looking at polling data, it's that his non-polls data this year is garbage. "Endorsement points" is an absurd premise worse than most pbrower stuff.
No, from what I recall all his non-polls data is based on historical correlations. The endorsement points are weighed in based on how similar endorsements have correlated with vote share in the past.
And that just seems like basic sound methodology to me. Maybe the historical record was wrong or maybe this is just an outlier. Doesn't really make him an idiot or a fraud though.
Yeah, the short version is that, even when you control for polling, candidates with more endorsements X number of days before primary season starts are more likely to do well once the voting starts. The exact causal mechanism isn't necessarily clear, but I guess the idea is that endorsements are a proxy for "support from the party elites".
