Why is Reuters/Ipsos using an "adults" sample"

[Xandric77]

Many adults are not even eligible to vote. That's not even mentioning many adults are not even registered to vote, let alone likely to vote. We don't even know how many are likely to register to vote.

Then dumb people like Krystal Ball get all excited about it because she doesn't know anything about methodology.

Link to tweet

?s=19

[HerbChestnut]

1. 84% of respondents were registered to vote.

Link to the poll.

https://fingfx.thomsonreuters.com/gfx/mkt/12/8684/8604/Topline%20Reuters%202020%20Election%20Tracker%2011%2014%202019.pdf

EDIT: Before someone freaks out, Republicans were not asked about their preference in the Democratic primary.

[George II]

4. It's an online poll conducted in English, then the results were "weighted to balance demographics"..

For this survey, a sample of 2,235 adults age 18+ from the continental U.S.,
Alaska and Hawaii were interviewed online in English. The sample includes 958 Democrats, 848
Republicans, and 249 independents. Weighting was then employed to balance demographics to
ensure that the sample's composition reflects that of the adult population according to Census data
and to provide results intended to approximate the sample universe.

In other words, huge chunks of Americans were not included (i.e., those who don't have internet access and those who only speak other languages), and the results were "weighted" (i.e., manipulated)

[HerbChestnut]

5. LOL, manipulated.

Right. Let the unskewing begin.

[Hassin Bin Sober]

7. Bazinga!

[crazytown]

2. Oh Ms Ball

what a gem you are.

[NurseJackie]

3. Would that make it a Margin-of-Error +/- 16%??

[HerbChestnut]

6. MoE was 2.4%. Thanks for playing.

[ritapria]

8. When you poll "adults", the results skew toward Benie

WaPo/ ABC News poll adults ...That number show shows him at 19% …..When they drill down to "registered voters" his support number drops to 17% ….

[JoeOtterbein]

9. K n R

Great news for Bernie!

Thanks for posting!