Estimating standard deviation
overview      

For Power and Sample Size calculations, the estimate of s (the population standard deviation or experimental variability) depends on whether you have already collected data.

·    Prospective studies are done before collecting data so s  has to be estimated. You can use related research, pilot studies, or subject-matter knowledge to estimate s.

·    Retrospective studies are done after data have been collected so you can use the data to estimate s.

-    For 1-Sample Z or 1-Sample t, use the standard deviation of the sample.

-    For 2-Sample t, use the pooled standard deviation (Pooled StDev).

-    For Paired t, use the standard deviation of the paired differences.

-    For One-way ANOVA, 2-Level Factorial Design, and Plackett-Burman Design, use the square root of the mean square error (MS Error).

For sample size calculations, the data have not been collected yet so s has to be estimated. You can use related research, pilot studies, or subject-matter knowledge to estimate s.