To Participate on Thurstonblog

email yyyyyyyyyy58@gmail.com, provide profile information and we'll email your electronic membership


Wednesday, October 12, 2016

Hmmm, isn't it logical that this respondent should be removed from the sample?

...................................................................................................................................................................
How a single 19-year-old man in Illinois wildly skewed a major poll towards Trump
By Jeva Lange, October 12, 2016

A lone 19-year-old black man in Illinois is single-handedly (and unknowingly) changing the standings of the presidential election, The New York Times has found. Due to the 19-year-old Trump supporter's inordinate weight in a USC Dornsife/Los Angeles Times Daybreak panel, his poll answers are directly affecting national averages, like the one compiled by RealClearPolitics.

The New York Times' Upshot blog breaks it down:
In some polls, [the 19-year-old is] weighted as much as 30 times more than the average respondent, and as much as 300 times more than the least-weighted respondent.

Alone, he has been enough to put Mr. Trump in double digits of support among black voters. He can improve Mr. Trump's margin by 1 point in the survey, even though he is one of around 3,000 panelists.

He is also the reason Mrs. Clinton took the lead in the USC/LAT poll for the first time in a month on Wednesday. The poll includes only the last seven days of respondents, and he hasn't taken the poll since Oct. 4. Mrs. Clinton surged once he was out of the sample for the first time in several weeks. [The New York Times]
Surveys are typically weighted to account for differences in population demographics, like age, race, or sex; the USC/Los Angeles Times poll fluctuates so wildly because it weights very small groups and it also by past votes. Yet in the USC/Los Angeles Times poll's defense, it is "extremely and admirably transparent," which allowed for the critical breakdown done by The New York Times, which you can read here.
...................................................................................................................................................................

No comments: