Timeline for Why are pre-election polls even less accurate on 2020 Presidential election comparing to 2016?
Current License: CC BY-SA 4.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 25, 2023 at 23:54 | history | reopened |
user149408 convert Apoliticalboy Timur Shtatland SurpriseDog |
||
| Jun 25, 2023 at 13:44 | review | Reopen votes | |||
| Jun 25, 2023 at 23:54 | |||||
| Nov 5, 2020 at 21:01 | comment | added | SurpriseDog |
"Results have margins of sampling error of 3.5 percentage points among registered voters and 4.0 among likely voters" In other words the results are so far outside of margin of error, the only thing one can conclude here is malice or incompetence.
|
|
| Nov 5, 2020 at 20:21 | comment | added | default locale | @SurpriseDog That's what I'm talking about. For this poll they interviewed 906 people in Wisconsin. The coverage is abysmally small and the 95% interval must be extremely wide, say -30..+30. Pollsters did their job: they asked people questions and published their answers. It's just that their result (+17) is quite meaningless as a prediction if we don't know the margin of error. | |
| Nov 5, 2020 at 20:04 | review | Reopen votes | |||
| Nov 6, 2020 at 15:24 | |||||
| Nov 5, 2020 at 19:50 | comment | added | SurpriseDog | @defaultlocale In Wisconsin an A+ rated ABC poll had Biden at +17!! and Nate Sliver defended it. fivethirtyeight.com/features/… The reality is more like +0.6% How any can trust polling after this is a mystery. | |
| Nov 5, 2020 at 19:46 | comment | added | SurpriseDog | Certainly looks like a systematic effect to me. Before the election, I was estimating the shy trumper effect at +6% based on this study: cloudresearch.com/resources/blog/… | |
| Nov 5, 2020 at 19:35 | history | closed |
Azor Ahai -him- divibisan Martin Schröder Glorfindel Rick Smith |
Not suitable for this site | |
| Nov 5, 2020 at 17:44 | comment | added | default locale | The pollsters really need to release a 90% confidence interval instead of a single number. We have no way to estimate how unlikely was a 5% error in a close race. | |
| Nov 5, 2020 at 16:51 | review | Close votes | |||
| Nov 5, 2020 at 19:35 | |||||
| Nov 5, 2020 at 16:08 | comment | added | jeffronicus | @JoeC Nate Silver was just tweeting the same point. | |
| Nov 5, 2020 at 16:08 | comment | added | Be Brave Be Like Ukraine | @JoeC, I agree. Looking for a canonical answer that may require time and effort to gather sufficient appropriate evidence. | |
| Nov 5, 2020 at 16:05 | comment | added | Joe C | Given there is a large number of the vote still outstanding, and we know that the outstanding vote is expected to be biased towards Biden, it is too early to be doing any polling retrospectives. | |
| Nov 5, 2020 at 16:00 | history | asked | Be Brave Be Like Ukraine | CC BY-SA 4.0 |