Timeline for US Election results 2016: What went wrong with prediction models?
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 7, 2019 at 0:10 | history | edited | gung - Reinstate Monica | CC BY-SA 4.0 |
link is dead; some will find the name-calling insulting
|
| S May 27, 2019 at 18:38 | history | mod moved comments to chat | |||
| S May 27, 2019 at 18:38 | comment | added | gung - Reinstate Monica | Comments are not for extended discussion; this conversation has been moved to chat. | |
| Nov 11, 2016 at 6:59 | comment | added | Has QUIT--Anony-Mousse | Oh, it's a priceless story. On some days, you have to laugh, rather than worry why prediction results are inaccurate. | |
| Nov 11, 2016 at 2:44 | comment | added | Jared Smith | @Anony-Mousse no matter how accurate it may or may not be, I fail to see how juvenile name-calling is relevant to statistical analysis. | |
| Nov 10, 2016 at 21:36 | comment | added | Has QUIT--Anony-Mousse | If it only were just a "crazy" answer. The problem is that it is systematic not "random crazy". You could consider the election a binary poll, and what "crazy answers" could you expect in binary? But apparently, a lot of people deliberately (?) give a wrong answer, or decide differently when actually in the booth, or then don't go to the elections, ... | |
| Nov 10, 2016 at 21:34 | history | edited | gung - Reinstate Monica | CC BY-SA 3.0 |
much as I agree... we still have a policy against this
|
| Nov 10, 2016 at 21:31 | history | edited | Has QUIT--Anony-Mousse | CC BY-SA 3.0 |
added 574 characters in body
|
| Nov 10, 2016 at 21:22 | comment | added | whuber♦ | I call this the "lunatic fringe principle" of polling: in any survey question, 5% of all respondents will give a crazy answer. Like any empirical principle it has exceptions, but it has stood up well for decades in helping make sense of poll results. | |
| Nov 10, 2016 at 21:18 | history | answered | Has QUIT--Anony-Mousse | CC BY-SA 3.0 |