FNChygernd

FNChygernd random arrays from the Fisher non central hypergeometric distribution.

Syntax

  • r=FNChygernd(M,K,n,odds)example
  • r=FNChygernd(M,K,n,odds, mm)example
  • r=FNChygernd(M,K,n,odds, mm,nn)example
  • r=FNChygernd(M,K,n,odds, mm,nn,oo)example

Description

example

r =FNChygernd(M, K, n, odds) Generate a random number from Wallenius non central hypergeometric distribution.

example

r =FNChygernd(M, K, n, odds, mm) A difficult example which needs to avoid underflow/overflow.

example

r =FNChygernd(M, K, n, odds, mm, nn) Generate a matrix of size mmxnn of random number from Fisher non central hypergeometric distribution.

example

r =FNChygernd(M, K, n, odds, mm, nn, oo) Generate a 3D array of size mmxnnxoo of random number from Fisher non central hypergeometric distribution.

Examples

expand all

  • Generate a random number from Wallenius non central hypergeometric distribution.
  • M=80; total number of balls n=10; number of balls taken odds=3; Prob. of red balls vs other color balls K=50; Number of red balls in the urn samplesize=100000; Sample size to extract

    edges=(0:(n+1))';
    % Generate a random number from the distribution above
    x=FNChygernd(M,K,n,odds);
    disp(x)

  • A difficult example which needs to avoid underflow/overflow.
  • M=8000; total number of balls n=2000; number of balls taken odds=3; Prob. of red balls vs other color balls K=5000; Number of red balls in the urn Generate an array of size 2x3x5 of random numbers from the distribution above

    mm=2;   nn=3; oo=5;
    rng(12345)
    X=FNChygernd(M,K,n,odds);
    disp(X)

  • Generate a matrix of size mmxnn of random number from Fisher non central hypergeometric distribution.
  • M=80; total number of balls n=10; number of balls taken odds=3; Prob. of red balls vs other color balls K=50; Number of red balls in the urn Generate a matrix of size 3x5 of random numbers from the distribution above

    mm=3;
    nn=5;
    X=FNChygernd(M,K,n,odds, mm,nn);
    disp(X)

  • Generate a 3D array of size mmxnnxoo of random number from Fisher non central hypergeometric distribution.
  • M=800; total number of balls n=200; number of balls taken odds=3; Prob. of red balls vs other color balls K=500; Number of red balls in the urn Generate an array of size 2x3x5 of random numbers from the distribution above

    mm=2;   nn=3; oo=5;
    X=FNChygernd(M,K,n,odds, mm,nn,oo);
    disp(X)

    Related Examples

    expand all

  • Comparison density and relatived frequencies based on random numbers.
  • close all
    M=100; % total number of balls
    n=10;  % number of balls taken
    odds=2; % Prob. of red balls vs other color balls
    K=50; % Number of red balls in the urn
    samplesize=100000; % Sample size to extract
    edges=(0:(n+1))';
    % Compute the density
    Fpdf=FNChygepdf(edges(1:end-1),M,K,n,odds);
    % Generate random numbers
    x=FNChygernd(M,K,n,odds,samplesize);
    % bar plot of theoretical and relative frequencies
    freqANDdens=[(histcounts(x,edges-0.5)/samplesize)' Fpdf];
    bar(edges(1:end-1),freqANDdens)
    legend(["Theoretical density" "Empirical relative frequency"],'Location','best')
    xlabel('Number of successes')
    Click here for the graphical output of this example (link to Ro.S.A. website)

    Input Arguments

    expand all

    K — Initial number of red balls in the urn. Scalar.

    Data Types: single|double

    n — Total number of balls sampled. Scalar.

    Data Types: single|double

    Optional Arguments

    mm — Length of first dimension. Scalar.

    Number of rows of the array which contains the random numbers

    Example: 3

    Data Types: double

    nn — Length of second dimension. Scalar.

    Number of columns of the array which contains the random numbers.

    Example: 2

    Data Types: double

    oo — Length of third dimension. Scalar.

    Number of 3D slides of the array which contains the random numbers

    Example: 5

    Data Types: double

    Output Arguments

    expand all

    r —Random numnbers. Array of random numbers from the Fisher non central hypergeometric distribution

    The size of rr is determined by the optional input parameters mm, nn, oo.

    References

    Fog, A. (2008), Calculation Methods for Wallenius' Noncentral Hypergeometric Distribution, "Communications in Statistics - Simulation and Computation", Vol. 37, pp. 258-273.

    This page has been automatically generated by our routine publishFS