The possible difference between your sample statistics and the actual
population statistics are dependent on the sample size.
Decide your tolerance for error (say a confidence interval of + or -
5%) and choose an appropriate sample size.
You can only work with sample sizes less than or equal to 30 when the
population is normally distributed and you know the population
standard deviation.
For larger samples, the standard deviation of the sample can be used
as an estimate of the Standard Deviation of the population.
When you don't have a population close to a Standard Normal
Distribution, you can use Student's t distribution.
Donna
[EMAIL PROTECTED]
On 27-Jun-07, at 7:06 PM, Raul Miller wrote:
your problem is that you've not collected enough data to
properly represent deviation
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm
