News for hackers. Stuff that matters.

A comment on How Good Are FiveThirtyEight Forecasts?. Parent comment

Re:How Good Are FiveThirtyEight Forecasts? by objektif on Friday April 26, 2019 @10:39AM (#19757989)
If thats your understanding of making a prediction then he was accurate by your standards. You clearly did not watch the election night predictions. NYT live model was miles better than 538s.

https://fivethirtyeight.com/features/how-i-acted-like-a-pund...

[ Parent | on HN ]
Re:How Good Are FiveThirtyEight Forecasts? by novia on Friday April 26, 2019 @11:10AM (#19758311)
Your link is from 2016 before the presidential election but after the primaries. Nate is admitting that he underestimated Trump in the primaries and talks about what happened. This does not seem particularly relevant to the subject of election night predictions.
[ Parent | on HN ]
Re:How Good Are FiveThirtyEight Forecasts? by objektif on Friday April 26, 2019 @11:19AM (#19758420)
This is regarding his bias. If anything the link is even more relevant. He repeated the similiar mistakes.
[ Parent | on HN ]
Re:How Good Are FiveThirtyEight Forecasts? by pwinnski on Friday April 26, 2019 @11:25AM (#19758485)
His main mistake as highlighted in that article is that they didn't use statistics for the nomination process, but guesswork. For the election proper, they did use statistics. So no, they did not repeat the mistake at all.
[ Parent | on HN ]
Re:How Good Are FiveThirtyEight Forecasts? by notheruser on Friday April 26, 2019 @11:40AM (#19758656)
His election night model wasn't good, but he isn't known and respected for his election night model, so who cares?
[ Parent | on HN ]