Algebraically, E = [z(a/2) / SQRT(n)] x SD, so it must be that the margin of error (maximum error as you called it) is a multiple of the population standard deviation. Keep in mind what these values represent. E is the margin of error of the estimate of mu, the population mean. SD is the population standard deviation. So, what you are asking becomes "Is the margin of error of an estimate for the population mean a fraction of the population standard deviation?" Does it make sense to even ask that question? Furthermore, if you know the population SD, you have enough information to calculate the population mean, so why estimate it? In otherwords, the "SD" you use in the formula is generally only an estimate of sigma itself. In practice, we can only estimate sigma. Using an algebraic "trick" to eliminate the need for getting a good estimate for sigma doesn't make sense to me. It sounds like your suggestion (although technically correct) would only cloud the real issue of either 1) estimating the population mean or 2) calculating the sample size needed to find such an estimate. I am not able to see the efficacy of your suggestion. Barry Edwards
"John Jackson" <[EMAIL PROTECTED]> wrote in message J%4t7.57364$[EMAIL PROTECTED]">news:J%4t7.57364$[EMAIL PROTECTED]... > Really sorry. > > My formula is a rearrangement of the confidence interval formula shown below > for ascertaining the maximum error. > > E = Z(a/2) x SD/SQRT N > > The issue is you want to solve for N, but you have no standard deviation > value. > > The formula then translates into n = (Z(a/2)*SD)/E)^2 Note: ^2 stands for > squared. > > You have only the confidence interval, let's say 95% and E of 1%. Lets say > that you want to find out how many people in the US have fake drivers > licenses using these numbers. How large (N) must your sample be? > > Do you have to hypothesize a US population to solve this, ie. 300 m or can > you solve it another way. It was suggested you can express the SD as a > fraction of the E. ie. E = SD/2. > > > > "Randy Poe" <[EMAIL PROTECTED]> wrote in message > [EMAIL PROTECTED]">news:[EMAIL PROTECTED]... > > John Jackson wrote: > > > > > the forumla I was using was n = (Z?/e)^2 and attempting to express .05 > as a > > > fraction of a std dev. > > > > I think you posted that before, and it's still getting > > garbled. We see a Z followed by a question mark, and > > have no idea what was actually intended. > > > > - Randy > > ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================
