 |
|
That does not support your case. In fact, it supports mine..
Posted on: November 4, 2016 at 11:30:37 CT
JeffB MU
Posts:
72172
Member For:
21.41 yrs
Level:
User
M.O.B. Votes:
0
that trying to save money by polling fewer people and then massaging the numbers to make up for undersampling or oversampling can create additional errors.
The way to fix that and to be more accurate is to poll more people and to do so completely randomly. Instead, they deliberately try to target sub groups and get their numbers into the mix or to massage the numbers after the fact to make up for under or over sampling.
From your link:
Gallup Explains How It Blew the Presidential Election
https://www.bloomberg.com/news/articles/2013-06-04/gallup-explains-how-it-blew-the-presidential-election
2. It blew the geography. By not interviewing enough people in certain regions of the country, specifically “the Eastern time zone within the Midwestern and Southern regions” and the “Pacific time zone within the Western region” (according to the report), it got a distorted picture of the race.
Duh. Random sampling a large enough sample would fix that problem.
3. It messed up race and ethnicity. Gallup forced people to answer a series of yes/no questions about their race and ethnicity that didn’t yield an accurate picture, and then assumed minorities would make up a smaller share of the vote than they actually did.
Same fix. Do it right. Get a large enough random sample.
4. It used a shortcut that didn’t work. For years, pollsters have relied on “random-digit dialing” (RDD) to reach both listed and unlisted numbers. This is expensive but, many pollsters believe, necessary since 45 percent of numbers are unlisted. Some recent academic research has indicated that it might be possible to get an accurate view of the electorate by scrapping RDD and combining (much cheaper) published phone numbers and cell phone users. (Huffington Post’s polling editor, Mark Blumenthal, has a thorough explainer here.) Gallup attempted this, and it didn’t work.
Again, it is the cost saving shortcuts that damaged the accuracy of the poll.
Edited by JeffB at 11:33:38 on 11/04/16
The way to fix that and to be more accurate is to poll more people and to do so completely randomly. Instead, they deliberately try to target sub groups and get their numbers into the mix or to massage the numbers after the fact to make up for under or over sampling.
From your link:
Gallup Explains How It Blew the Presidential Election
https://www.bloomberg.com/news/articles/2013-06-04/gallup-explains-how-it-blew-the-presidential-election
2. It blew the geography. By not interviewing enough people in certain regions of the country, specifically “the Eastern time zone within the Midwestern and Southern regions” and the “Pacific time zone within the Western region” (according to the report), it got a distorted picture of the race.
Duh. Random sampling a large enough sample would fix that problem.
3. It messed up race and ethnicity. Gallup forced people to answer a series of yes/no questions about their race and ethnicity that didn’t yield an accurate picture, and then assumed minorities would make up a smaller share of the vote than they actually did.
Same fix. Do it right. Get a large enough random sample.
4. It used a shortcut that didn’t work. For years, pollsters have relied on “random-digit dialing” (RDD) to reach both listed and unlisted numbers. This is expensive but, many pollsters believe, necessary since 45 percent of numbers are unlisted. Some recent academic research has indicated that it might be possible to get an accurate view of the electorate by scrapping RDD and combining (much cheaper) published phone numbers and cell phone users. (Huffington Post’s polling editor, Mark Blumenthal, has a thorough explainer here.) Gallup attempted this, and it didn’t work.
Again, it is the cost saving shortcuts that damaged the accuracy of the poll.
Edited by JeffB at 11:33:38 on 11/04/16
Please explain why this message is being reported.
MESSAGE THREAD
That does not support your case. In fact, it supports mine.. - JeffB MU - 11/4 11:30:37