CORRELATION

(Statistics) A statistical means to measure the degree of "coincidence of change" between two variables, producing a value of variance termed the Correlation Coefficient. In strict correlation analysis, no inference of causation, i.e., one variable being "explained" by the variations of another, is made. Therefore, high correlations do not provide for an inference of causality; one must use previous information that the two sampled variables are indeed related to one another. The concept of the Coefficient of Determination, on the other hand, used as a common measure of "Goodness of Fit" in Regression Analysis, is used to assess the degree of causation between two variables or between one or more independent variables and a single dependent variable. The coefficient of determination is equivalent to the square of the correlation coefficient and reflects the percent of change in the dependent (explained) variable that is explained by the variations in the independent (explanatory) variable.