Next: , Previous: DRANDEXPONENTIAL, Up: Continuous Univariate Distributions

DRANDF / SRANDF

Generates a vector of random variates from an F distribution, also called the Fisher's variance ratio distribution, with probability density function, f(X), where: f(X) = [((m + v - 2) / 2)! * X^(m / 2 - 1) * m^(m / 2)] / [(m / 2 - 1)! * (v / 2 - 1)! * (1 + m * X / v)^((m + v) / 2) * v^(m / 2)], if X > 0, otherwise f(X) = 0. Here m is the first degrees of freedom, (DF1) and v is the second degrees of freedom, (DF2).

(Note that SRANDF is the single precision version of DRANDF. The argument lists of both routines are identical except that any double precision arguments of DRANDF are replaced in SRANDF by single precision arguments - type REAL in FORTRAN or type float in C).

— SUBROUTINE: DRANDF (N,DF1,DF2,STATE,X,INFO)
— Input: INTEGER N

On input: number of variates required.
Constraint: N>=0.

— Input: INTEGER DF1

On input: first degrees of freedom.
Constraint: DF1>=0.

— Input: INTEGER DF2

On input: second degrees of freedom.
Constraint: DF2>=0.

— Input/Output: INTEGER STATE(*)

The STATE vector holds information on the state of the base generator being used and as such its minimum length varies. Prior to calling DRANDF STATE must have been initialized. See Initialization of the Base Generators for information on initialization of the STATE variable.
On input: the current state of the base generator.
On output: the updated state of the base generator.

— Output: DOUBLE PRECISION X(N)

On output: vector of variates from the specified distribution.

— Output: INTEGER INFO

On output: INFO is an error indicator. On successful exit, INFO contains 0. If INFO = -i on exit, the i-th argument had an illegal value. 

     Example:
     

     
          C      Generate 100 values from the F distribution
                 INTEGER LSTATE,N
                 PARAMETER (LSTATE=16,N=100)
                 INTEGER I,INFO,SEED(1),STATE(LSTATE)
                 INTEGER DF1,DF2
                 DOUBLE PRECISION X(N)
          C      Set the seed
                 SEED(1) = 1234
          
          C      Read in the distributional parameters
                 READ(5,*) DF1,DF2
          
          C      Initialize the STATE vector
                 CALL DRANDINITIALIZE(1,1,SEED,1,STATE,LSTATE,INFO)
          C      Generate N variates from the F distribution
                 CALL DRANDF(N,DF1,DF2,STATE,X,INFO)
          
          C      Print the results
                 WRITE(6,*) (X(I),I=1,N)