Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Politics : Electoral College 2000 - Ahead of the Curve -- Ignore unavailable to you. Want to Upgrade?

To: Nichols who wrote (84)	10/25/2000 9:15:07 AM
From: Vendit™	Read Replies (1) \| Respond to of 6710

Slightly off topic: Rasmussen Research is an independent public opinion and market research firm. The company does not work for for candidates, political parties, and elected officials. An independent analysis conducted by the Progressive Review found Rasmussen Research polls were the most accurate in terms of projecting actual election outcomes during the recently concluded Presidential Primaries. Gallup and Zogby were second and third. In every primary projected, the leader in the final Rasmussen Research survey emerged victorious on election day. Through last night Bush leads Gore by 7. portraitofamerica.com

To: Nichols who wrote (84)	10/25/2000 2:56:52 PM
From: Cisco	Read Replies (2) \| Respond to of 6710

Any thoughts why all major polls see Gore getting momentum and and extremely close race while the voter.com poll still registers Bush with a big lead. I am so glad you asked that question. I believe this is one of the most misunderstood aspects of polling. A poll is only as good as the methodology it uses! A methodology that works the best one election year probably will not work as well the next election year unless it is modified. Consider the following factors in polling methodology: 1. Sample size: the larger the sample size the better the opportunity for the poll results to be good. 2. How is the Poll taken: automated or by person? 3. How is the sample weighted: Once data is collected, the sample most be weighted by (i.e. age, race, sex, political party, geographical location, etc.). The poll that can design their methodology to reflect who is actually going to vote will provide the best prediction. 4. Is the poll weighted for registered voters, likely voters, or a mixture of both? For example CBS's tracking poll of likely voters is actually weighted heaver for registered voters. 5. What questions does the poll use to determine if a voter is really a likely voter or not. These screening questions may include questions about their voting history, their intentions to vote in the upcoming election, and other matters. In a low voter turn out election, these questions become very important! 6. Does the methodology include using the same weighting each time. Believe it or not the Gallup organization doesn't even use the same percentage of Democratics and Republicans each night in their tracking poll. 7. Finally, a good tracking poll should provide consistent results from night to night. A poll that swings back and forth 3 or 4 points or more on no news has something wrong with its methodology. I like the Rasmussen Research's Portrait of America poll the best this political year for the reason cited by Vendit earlier: In every primary (2000) projected, the leader in the final Rasmussen Research survey emerged victorious on election day. I don't trust the CBS or Gallup polls this year. I also have some problems with Zogby. I do like the voter.com battleground poll! Perhaps this answers some of your questions.