A statistic representing the degree of linear relationship between two variables. It is defined as the covariance of the two variables divided by the product of their standard deviations, hence it may be thought of as a measure of standardized (1) covariance. It is symbolized by r, and it ranges from 1.00 for perfect positive correlation, through zero for uncorrelated variables, to −1.00 for perfect negative correlation. When one variable is being used to predict another, the square of r indicates the proportion of variance in one variable that is explained by the other (given certain linear assumptions), or the proportion of variance shared by the two variables: if r = .50, then r2 = .25, indicating that 25 per cent of the variance in one of the variables is explained by the other, or that 25 per cent of the variance is shared by the two variables. Also called Pearson's correlation coefficient. See also correlation. Compare correlation ratio, partial correlation, Spearman rank correlation coefficient.