Date: Feb 28, 2013 1:00 AM
Author: Outspan
Subject: Re: Standard deviation over observed sample

On Wednesday, February 27, 2013 2:04:59 PM UTC+1, Dario Borghino wrote:

> I believe (correct me if I'm wrong) that the above graph cannot be used to answer this question at all. So how do I solve/compute this? Is this a trivial problem? Can I solve this analytically or do I have to use a computer simulation?

Does this make sense? In the graph I linked above, I am effectively rolling a 100-sided dice, and counting a score of 9 or below as a "hit" and everything else as a "miss". Therefore, the EV is 0.09, and the standard deviation can be calculated.

But in the second case--the one I'm actually interested in--I don't know what's the threshold for a "hit" or a "miss"--I merely observed that, after n samples (with a small n, for instance n=100), I happened to obtain a value of 0.09, but I have no reason to believe that this is the EV (n is small). How can I estimate the error? Is it the same as in the first case?

Again sorry about the terminology. Hopefully my question is clear.