The Cellar - View Single Post - 100,000 Iraqi Civilians have died in current war

Beestie · 01-31-2005, 12:34 PM

Why would someone use "sampling techniques" instead of an actual body count? Besides, statistics should only be applied to recurring events as they tend to zero in on the liklihood of an outcome over a number of observations.

I think, for example, there is more than a 99% confidence interval that the winning lottery ticket was not, in fact, a winner. Over time, the "99% of the time the ticket will not be a winner" conclusion will be proven correct. But you can't take an average and apply it to a single observation. At best, its meaningless and at worst, its very misleading.

Its been my experience that when stats meets politics, hold your nose.

01-31-2005, 12:34 PM	#8
Beestie -◊\|≡·∙■·∙≡\|◊- Join Date: Feb 2003 Location: Parts unknown. Posts: 4,081	Why would someone use "sampling techniques" instead of an actual body count? Besides, statistics should only be applied to recurring events as they tend to zero in on the liklihood of an outcome over a number of observations. I think, for example, there is more than a 99% confidence interval that the winning lottery ticket was not, in fact, a winner. Over time, the "99% of the time the ticket will not be a winner" conclusion will be proven correct. But you can't take an average and apply it to a single observation. At best, its meaningless and at worst, its very misleading. Its been my experience that when stats meets politics, hold your nose. __________________ ♠ ♥ ♣ ♦