From: Bobbi
Date: 09 Dec 2003
Time: 12:15:15
Walter,
Yes, I think I have the info. you need. Use this formula and solve for "E."
n = (K2 * sigma2) / E2
That's k squared times sigma squared, divided by E squared, where n is the sample size, K is the coefficient of normal distribution (for alpha 0.05, K is 1.96), sigma is the standard deviation, and E is the error.