Two-way Fisher F-test for analysis of variance (Anova)
  Entirely free download of software
                                The calculator gives the probability value of an F-test, given the F-value and
                                degrees of freedom of numerator (DF1) and denominator (DF2), as well as
                                the value of the F-test given the probability.
                                                        Screenprint of the two-way Fisher F-test calculator:
                                  here comes an image    

F-test calculator
F-distribution calculator

Go to:

& models

& manuals

case studies

& papers



More examples of F-test graphics

here comes an image

here comes an image

A numerical solution of Fisher's F- probability distribution is obtained when either DF1 or DF2 are even. (See reference below.)
When both are even, use the smallest. When both are uneven (odd) an approximate solution is to be found.
DF1 is even
        Pc = 1 - sn/2 [ 1 + n.t / 2 + n (n+2) t2 / 8 + n (n+2) (n+4) t3 / 48 + n (n+2 ) (n+4) (n+6) t4 / 384 . . . . . ]
s = n / (m+n.z), t = 1-s, m = DF1, n = DF2, z = reference value for the variable y following the F-distribution
      (like the F-test value itself),
Pc = cumulative probability that can also be represented by the probability P(y<z) that y is less than z.
The series of denominators 2, 8, 48, 384 . . . equals the series 2, 2x4, 2x4x6, 2x4x6x8 . . .
The number of terms between the parentheses [ ] to be used is n / 2.
DF2 is even
        Pc = tn/2 [ 1 + n.s / 2 + n (n+2) s2) / 8 + n (n+2) (n+4) s3 / 48 + n (n+2) (n+4) (n+6) s4 / 384 . . . . . ]
DF1 and DF2 are uneven (odd)
The above equations for Pc are, apart of z, a function of m and n, and can be represented as Pc(m,n).
When DF1=m and DF2=n are both uneven (odd), the cumulative probability Pc(m,n) can be approximated by non linear interpolation between Pc(m,n-1) and Pc(m,n+1).                                                                                                
The interpolation can be done with a weight factor (w):
        Pc(m,n) = { w.Pc(m,n+1) + Pc(m,n-1) } / (1+w)
Using w=3 one finds a reasonable approximation.
Reference: Casio, 1990. "Program library". Manual for Casio's programmable calculators. See online.

here comes an image

here comes an image

here comes an image

    The flowers are here
    to make the mathematics
    less boring.


eXTReMe Tracker