DiscoverFiveThirtyEight PoliticsModel Talk: Why Polls Were Off In 2020, And Why They Weren’t That Bad
Model Talk: Why Polls Were Off In 2020, And Why They Weren’t That Bad

Model Talk: Why Polls Were Off In 2020, And Why They Weren’t That Bad

Update: 2020-11-125
Share

Description

In this installment of "Model Talk," Nate and Galen discuss why a polling error of even four points isn't that unexpected, offer reasons for why the error occurred and discuss the usefulness of polling and modeling going forward.

Comments (2)

Saket Agarwal

delusional podcast. I have never seen them take any responsibility. I like how they are throwing polling industry under the bus. at this point, I wonder what value does 538 really adds. rcp avg = 538 model.

Nov 13th
Reply

thomas cherian

great podcadt

Nov 12th
Reply
00:00
00:00
x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

Model Talk: Why Polls Were Off In 2020, And Why They Weren’t That Bad

Model Talk: Why Polls Were Off In 2020, And Why They Weren’t That Bad

FiveThirtyEight, 538, ABC News, Nate Silver