The POWER and GLMPOWER procedures and the Power and Sample Size tasks in SAS^® Studio provide prospective power analysis and sample size computations to be used in the planning stages of an analysis. They do not perform retrospective power or sample size computations. Retrospective analysis is not available.

The following references discuss why retrospective power analysis should be discouraged:

Hoenig, J. M., and D. M. Heisey (2001), "The abuse of power: The pervasive fallacy of power calculations for data analysis," The American Statistician, 55:19–24.

Littell, R. C., G. A. Milliken, W. W. Stroup, R. D. Wolfinger, and O. Schabenberger (2005), SAS for Mixed Models, Cary, NC: SAS Institute Inc.

Thomas, L. (1997), "Retrospective power analysis." Conservation Biology, 11:276–280.