|
Printer-friendly format Email this thread to a friend Bookmark this thread |
This topic is archived. |
Home » Discuss » Archives » General Discussion: Presidential (Through Nov 2009) |
Bonobo (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:43 AM Original message |
500 people are enough for a representative sampling of the WHOLE COUNTRY!? |
Printer Friendly | Permalink | | Top |
mediaman007 (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:44 AM Response to Original message |
1. I''m not a statistician, but I can't imagine that 500 people |
Printer Friendly | Permalink | | Top |
Bucky (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 12:43 PM Response to Reply #1 |
33. I've studied statistics. And yes, within a margin of error, a scientific sampling works quite well. |
Printer Friendly | Permalink | | Top |
Stand and Fight (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:48 AM Response to Original message |
2. Funny thing is... |
Printer Friendly | Permalink | | Top |
TheKentuckian (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:52 AM Response to Reply #2 |
3. I'm thinking a representative sample |
Printer Friendly | Permalink | | Top |
EstimatedProphet (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:08 AM Response to Reply #3 |
12. Why? |
Printer Friendly | Permalink | | Top |
CTyankee (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:17 AM Response to Reply #12 |
30. The margin of error |
Printer Friendly | Permalink | | Top |
EstimatedProphet (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 02:14 PM Response to Reply #30 |
35. All other things being equal, yes. |
Printer Friendly | Permalink | | Top |
Tarc (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:52 AM Response to Original message |
4. Yes, but when most of the polls show the same or similar numbers |
Printer Friendly | Permalink | | Top |
Captain Hilts (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:56 AM Response to Reply #4 |
7. There's no big 'pollster conspiracy'. They don't work together. |
Printer Friendly | Permalink | | Top |
Captain Hilts (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:55 AM Response to Original message |
5. It must have a large margin of error. Gallup is a lazy pollster that doesn't balance its data well. |
Printer Friendly | Permalink | | Top |
Fluffdaddy (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:56 AM Response to Original message |
6. What, now that the polls are tightening up we are choosing not to believe them? |
Printer Friendly | Permalink | | Top |
grantcart (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 09:57 AM Response to Original message |
8. actually CNN's poll of polls shows Obama with his biggest national lead |
Printer Friendly | Permalink | | Top |
napi21 (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:02 AM Response to Original message |
9. 500 people CAN give an indication of multimillions IF the 500 |
Printer Friendly | Permalink | | Top |
Jackpine Radical (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:03 AM Response to Original message |
10. All polling hinges on the accuracy with which the sample represents the population. |
Printer Friendly | Permalink | | Top |
EstimatedProphet (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:06 AM Response to Original message |
11. It can be, if the trends are very defined |
Printer Friendly | Permalink | | Top |
Kurt_and_Hunter (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:11 AM Response to Original message |
13. Your "refutation by personal incredulity is noted" |
Printer Friendly | Permalink | | Top |
drm604 (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:20 AM Response to Original message |
14. Statisticians will disagree with you. |
Printer Friendly | Permalink | | Top |
AllentownJake (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:50 AM Response to Reply #14 |
18. +-4 |
Printer Friendly | Permalink | | Top |
drm604 (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:59 AM Response to Reply #18 |
23. I was going by the chart on isixsigma.com |
Printer Friendly | Permalink | | Top |
endthewar (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:07 AM Response to Reply #23 |
27. Here is the table that you should use to understand election polling: |
Printer Friendly | Permalink | | Top |
slackmaster (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:44 AM Response to Original message |
15. Yes, that is enough if the sample is properly stratified |
Printer Friendly | Permalink | | Top |
AllentownJake (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:48 AM Response to Reply #15 |
17. Actually it isn't |
Printer Friendly | Permalink | | Top |
slackmaster (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:51 AM Response to Reply #17 |
19. Yes, but for 95% +- 5% out of 100 million you need only 383 |
Printer Friendly | Permalink | | Top |
AllentownJake (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:52 AM Response to Reply #19 |
20. +-5 |
Printer Friendly | Permalink | | Top |
endthewar (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:01 AM Response to Reply #20 |
25. "That means they could be 10 points off." |
Printer Friendly | Permalink | | Top |
slackmaster (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 12:32 PM Response to Reply #20 |
32. +-3 doesn't seem much more useful to me |
Printer Friendly | Permalink | | Top |
endthewar (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:00 AM Response to Reply #17 |
24. "95% +-3" |
Printer Friendly | Permalink | | Top |
AllentownJake (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:06 AM Response to Reply #24 |
26. Sorry I do audit sampling |
Printer Friendly | Permalink | | Top |
endthewar (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:15 AM Response to Reply #26 |
29. Further explained |
Printer Friendly | Permalink | | Top |
AllentownJake (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:10 AM Response to Reply #24 |
28. BTW better read your own article |
Printer Friendly | Permalink | | Top |
endthewar (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 11:22 AM Response to Reply #28 |
31. The +/- 5 has NOTHING to do with the INTERPRETATION of an election poll |
Printer Friendly | Permalink | | Top |
AllentownJake (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:47 AM Response to Original message |
16. Enjoy the Sample Size Calculator! |
Printer Friendly | Permalink | | Top |
suston96 (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:55 AM Response to Original message |
21. Accurate? Which pollster ever claimed that their polling is "accurate"? |
Printer Friendly | Permalink | | Top |
endthewar (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 10:58 AM Response to Original message |
22. Very important table to help understand polling data |
Printer Friendly | Permalink | | Top |
Bucky (1000+ posts) Send PM | Profile | Ignore | Tue Aug-19-08 12:45 PM Response to Original message |
34. You are wrong in calling this bullshit. |
Printer Friendly | Permalink | | Top |
DU AdBot (1000+ posts) | Fri Sep 20th 2024, 05:22 PM Response to Original message |
Advertisements [?] |
Top |
Home » Discuss » Archives » General Discussion: Presidential (Through Nov 2009) |
Powered by DCForum+ Version 1.1 Copyright 1997-2002 DCScripts.com
Software has been extensively modified by the DU administrators
Important Notices: By participating on this discussion board, visitors agree to abide by the rules outlined on our Rules page. Messages posted on the Democratic Underground Discussion Forums are the opinions of the individuals who post them, and do not necessarily represent the opinions of Democratic Underground, LLC.
Home | Discussion Forums | Journals | Store | Donate
About DU | Contact Us | Privacy Policy
Got a message for Democratic Underground? Click here to send us a message.
© 2001 - 2011 Democratic Underground, LLC