convariance

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

In statistics, covariance is a measure of how closely two variable match one another. For two series xi and yi, the covariance is calcuated using the formula:
      cov(x,y) = ( Σ (xi - μx) × (yi - μy) ) / N.

Covariance is used in many contexts including in time-series analysis and the calcuations of a correlation matrix for dimension reduction of big data.