Hi,

your question is intriguing.

The problem of sample size is related to the precision in estimating various population's parameters starting from just a sample drawn from it.

If you think about, e.g., the estimate of population mean and the standard error value (which is equal to standard deviation divided by the square root of the sample size), you will understand that as long as the sample size increases, the standard error decreases. This leads to narrow down the Confidence Interval in which the "true" mean lies.

To go back to your question, I believe that you can find some hints at the following pages

http://en.wikipedia.org/wiki/Sample_size
http://en.wikipedia.org/wiki/Statistical_power
I believe, moreover, that a sample size of 80 (as in your case) is big enough to be considered "large".

By the way, when you perform hypothesis tests SigmaPlot gives you the statistical power of the test (that is the probability that the test will detect a difference if there really is a difference).

May be that other members of the Forum can give you deeper statistical insight into the issue.

I hope this helps,

regards

Gm