Categories &

Functions List

Function Reference: mvtpdf

statistics: y = mvtpdf (x, rho, df)

Multivariate Student’s t probability density function (PDF).

Arguments

  • x are the points at which to find the probability, where each row corresponds to an observation. (N×D matrix)
  • rho is the correlation matrix. (D×D symmetric positive definite matrix)
  • df is the degrees of freedom. (scalar or vector of length N)

The distribution is assumed to be centered (zero mean).

Return values

  • y is the probability density for each row of x. (N×1 vector)

Examples

 
 x = [1 2];
 rho = [1.0 0.5; 0.5 1.0];
 df = 4;
 y = mvtpdf (x, rho, df)

References

  1. Michael Roth, On the Multivariate t Distribution, Technical report from Automatic Control at Linkoepings universitet, http://users.isy.liu.se/en/rt/roth/student.pdf

Input arguments must be double or single; integer, logical, and character arrays are rejected. MATLAB accepts a character array and evaluates it at the character codes, which Octave deliberately does not, since a character array is an integer type and integers are refused too.

See also: mvtcdf, mvtrnd

Source Code: mvtpdf

Compute the pdf of a multivariate t distribution with correlation parameters rho = [1 .4; .4 1] and 2 degrees of freedom.

 rho = [1, 0.4; 0.4, 1];
 df = 2;
 [X1, X2] = meshgrid (linspace (-2, 2, 25)', linspace (-2, 2, 25)');
 X = [X1(:), X2(:)];
 y = mvtpdf (X, rho, df);
 surf (X1, X2, reshape (y, 25, 25));
 title ('Bivariate Student''s t probability density function');
plotted figure