Version:

Last Modified: January 9, 2017

Computes the covariance matrix of a sequence.

The input sequence. Each column of **x** represents one vector of observed samples from one variable. Each row of **x** represents an observation from each variable.

Error conditions that occur before this node runs. The node responds to this input according to standard error behavior.

**Default: **No error

Covariance matrix of the input sequence.

If **x** is an *n*-by-*m* 2D array, then the covariance matrix is a square *m*-by-*m* matrix.

Mean of each column variable in the input sequence.

Given *m* vectors of observed samples where the *i*^{th} column contains the variate *x*_{i}, the covariance matrix is defined as:

${v}_{ij}=({x}_{i}-{\mu}_{i})({x}_{j}-{\mu}_{j})$

where
${\mu}_{i}$ is the mean of variate *x*_{i}.

Each element *v*_{ij} of **covariance matrix v** is the covariance between variates *x*_{i} and *x*_{j}. The diagonal of **covariance matrix v** contains the standard variances of each *x*_{i} variate.

**mean vector** returns the computed mean of each variate as shown by the following equation:

${\mathrm{mean}\text{\hspace{0.17em}}\mathrm{vector}}_{i}={\mu}_{i}$

**Where This Node Can Run: **

Desktop OS: Windows

FPGA: Not supported