CL_cor2cov

Description

• Computes the covariance matrix from the correlation matrix and the standard deviation vector.

  The covariance matrix is defined as follows:

  - covm(i,i) = sd(i)^2

  - covm(i,j) = corm(i,j) * sd(i) * sd(j)

  Notes:

  - The correlation matrix should be symetrical (not checked).

  - An error is raised if one diagonal term is not 1.

  - An error is raised if one standard deviation value is not positive.

Parameters

corm:

Correlation matrix (NxNxK)

sd:

Standard deviation vector (NxK)

covm:

Covariance matrix (NxNxK)

Authors

• CNES - DCT/SB

See also

• CL_cov2cor

Examples

corm = [1, 0, 0.5; 0, 1, -0.8; 0.5, -0.8, 1]; sd = [1; 2; 3]; covm = CL_cor2cov(corm, sd); // Consistency check: [corm2, sd2] = CL_cov2cor(covm)