Hi Micha,

I send the file with data via email.

1. Calculations manually in Matlab under known formulas to 6 signs after a comma coincide with calculations in version 3.3.20130114, and differ even in 2 sign in the version
3.4.201304118 (see more low). The high-rise network, 9 measurements of 5 superfluous measurements an α = 0,05, β = 0,8 was adjust. It is clear that so should not be. Then that I have not considered?

and

2. Me interests how to calculate only Kprio = F(m,∞,1-α), Kpost = F(m,f-m,1-α). Using statistical tables of F-distribution of Fisher or corresponding functions for distribution from Matlab, for m=1, 2, 3, f=5 and α = 0,05 for a network from an example it is had

Kprio = F(1,∞,1-0,05)= 3,841 – True                   Kpost = F(1,5-1,1-0,05) = 7,709 – Not true.
Kprio = F(2,∞,1-0,05)= 2,996 – Not true               Kpost = F(2,5-2,1-0,05) = 9,552 – Not true.
Kprio = F(3,∞,1-0,05)= 2,605 – Not true               Kpost = F(3,5-3,1-0,05) = 19,164 – Not true.

Why? What do I do not so and how it is necessary?

regards
Alexander