The extent of the relationship between two variables. It is an inherently algebraic concept and cannot be defined without reference to algebra. Where variables have been normalized the covariance is equal to the correlation.

The covariance between two *jointly distributed* numeric *random variables*, *X* and *Y* with expectations is defined as:

\[\begin{align} Covariance(X,Y) = \operatorname{E}{\big[(X - \operatorname{E}[X])(Y - \operatorname{E}[Y])\big]}\end{align}\]

Where \(x_i\) and \(y_i\) are the realized values of *X* and *Y* in a sample of *n* observations and \(\bar{x}\) and \(\bar{y}\) are their respective means, the sample covariance is estimated as:

\[\begin{align} Covariance(x,y) = \frac{1}{n-1}\sum^n_{i=1}(x_i - \bar{x})(y_i - \bar{y})\end{align}\]

## Comments

0 comments

Article is closed for comments.