Timeline for Why did polls inaccurately predict the 2015 UK general election?
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 24, 2017 at 19:03 | comment | added | indigochild | @Bregalad - You are describing self-selection bias. | |
| Apr 20, 2017 at 10:51 | comment | added | HomoTechsual | Interesting point, though I'm almost certain that polling groups will keeping asking the questions until they get responses from the number of people in each "sample group" would this not eliminate that bias? | |
| Apr 20, 2017 at 10:31 | comment | added | Bregalad | Well, in an hypotetical case were 50% of people will vote for A and 50% of people will vote for B, but 60% of people going to vote for A will refuse to answer a poll and only 40% of people voting B will refuse to answer. The poll will predict B will win over A because more people voting for B answered the poll, but the poll was biased in the 1st place, because the pool that answered the poll weren't representative of the pool of voters. | |
| Apr 20, 2017 at 10:25 | comment | added | HomoTechsual | @Bregalad Are you alluding to the "Shy Tory/Shy UKIP/Shy *) factor? en.wikipedia.org/wiki/Shy_Tory_Factor It's worth noting that an enquiry by the British Polling Council found that this wasn't a factor in the 2015 General. | |
| Apr 20, 2017 at 9:13 | comment | added | Bregalad | But isn't there some inherent bias, for example people voting a certain way being more likely to refuse answering the poll ? | |
| Apr 20, 2017 at 9:10 | history | answered | Yosef Mordechai Coleman | CC BY-SA 3.0 |