This statlet determines the required sample size for comparing the means of several normal distributions. The tabs are:
The input tab permits you to specify information about the estimation or test you wish to perform:
Enter:
Hypothesized difference - the hypothesized value of the maximum difference between any two population means. This is used only if the Power button is selected.
Assumed within-group sigma - the standard deviation of the populations, assumed to be the same for all populations.
Number of means - the number of group means to be compared.
Tolerance - if selected, the sample size necessary to achieve Tukey HSD intervals of the specified width will be determined.
Power - if selected, the sample size necessary to achieve an F test with the indicated power in a oneway ANOVA will be determined. Specify the probability of a Type I error (alpha), the probability of a Type II error (beta), and the alternative at which the power will be controlled. If the desired test is two-sided, be sure the checkbox labeled "Two-sided" is checked.
For more details on hypothesis tests, see the Glossary.
This tab shows the sample size needed to meet the requirements entered on the input panel:
This tab shows the power curve for the determined sample size:
The power curve shows the probability of rejecting the null hypothesis as a function of the true maximum difference between the population means.