Not looking for a solution, just wonder what formula to use (and why?):

Given population A and population B, where:

standard deviation(A) = standard deviation(B) = $100$

If I select equal sample size N from A and B, how big does the sample size need to be to estimate the difference in population mean to within $10$ with 99% confidence?

My attempt:

If both of the population standard deviations are known, then the formula for a confidence interval for the difference between two population means (averages) is

$\bar{x_1} - \bar{x_2} \pm z\sqrt{\frac{\sigma_1^2}{n_1} + \frac{\sigma_2^2}{n_2}}$

Where $\bar{x_1} - \bar{x_2}$ is the difference in the sample means. We know the sample sizes are the same:

$n_1 = n_2 = N$

And the z value for 99% confidence level is 2.58, so:

$\bar{x_1} - \bar{x_2} \pm 2.58\sqrt{\frac{100^2 +100^2}{N}}$

Is $\pm 2.58\sqrt{\frac{100^2 +100^2}{N}}$ the margin of error? Then solving:

$10 = \pm 2.58\sqrt{\frac{100^2 +100^2}{N}}$ yields $N = 1331.28$. Am I on the right track here?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.