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 : American Presidential Politics and foreign affairs -- Ignore unavailable to you. Want to Upgrade?

To: DuckTapeSunroof who wrote (45305)	8/26/2010 6:03:24 PM
From: TimF	Read Replies (1) \| Respond to of 71588

A finding is said to be statistically significant if it is determined that it is sufficiently unlikely to occur by random chance. Sufficiently unlikely often means "no more than 5% chance", but it can be some other level. A "statistically significant" finding, doesn't mean that the finding is absolutely correct. Even if you use one in a thousand rather than 5% as your criteria, you could hit that one in a thousand case. Similarly a finding that isn't statistically significant, doesn't mean a finding that is false, or even unlikely. If you pick 5% as your level, and its only 90% chance that its not a random fluctuation, than it still probably isn't randomness. There probably is something there. But you have to set some level. Getting back to the subject at hand, the margin of error for the polls is almost certainly not as large as the difference between Reagan and Obama at this point in their presidencies. Sure that difference may shrink, going down to within the margin of error, but it might also expand. Guessing it will shrink in the remainder of Obama's 2nd year is just speculation.