test power estimates

Let there be two gamma distributions with parameters that fall to one of the following six scenarios: scenario 1 ..both shape parameters are 1..10, scenario 2..both shape parameters are 11..20, scenario 3.. both shape params are 21..30, scenario 4..shape 1 is 1..10, shape 2 is 11..20,scenario 5..shape 1 is 1..10, shape 2 is 21..30, scenario 6..shape 1 is 11..20, shape 2 is 21..30. The scale 1 parameter is always 1..30, and the scale 2 parameter is such that: in scenario 1, the expected values of the two gamma distributions always differ by 20, in scenario 2, the expected values of the two gamma distributions differ by 30, in scenario 3, the expected values of the two gamma distributions differ by 38, in scenario 4, the expected values of the two gamma distributions differ by 14, in scenario 5, the expected values of the two gamma distributions differ by 16, in scenario 6, the expected values of the two gamma distributions differ by 28. Obtaining by simulation many pairs of random samples from the two gamma distributions, a test can be carried out to test the null hypothesis: both expected values are the same. Using the many pairs, the test power can be estimated. These estimates are contained in the files "power_sc number1_number2. xls", where number2 is the sample size (both samples of equal size), number1 = parameter scenario. Each such file contains the test power estimates, each estimate related to a specific sc number1 set-up of the parameters of the two distributions.