Definition Coefficient of correlation

In statistics, a coefficient of correlation reflects the strength and direction of a linear relationship or dependence between two cardinal or ordinal variables. The correlation coefficient always lies between -1 and +1. A value of -1 indicates an entirely negative correlation. A correlation coefficient cannot be calculated for a nominal scale.

An example:

Every day, a person spends $100. At the end of day 10, the person has $1,000 less Dollars in his wallet than on the first day. Between the variable 'possession of money' and 'day', there is a completely negative correlation.

The value +1 indicates an entirely positive correlation. In this case, the person would earn $100 every day – so that on day 10, he would have earned $1,000.

The value 0 indicates that there is no demonstrable relationship between two variables at all.

As a rule, one would speak of a statistically discernible interdependance, if values met or exceeded +0.6/-0.6.

Please note that the definitions in our statistics encyclopedia are simplified explanations of terms. Our goal is to make the definitions accessible for a broad audience; thus it is possible that some definitions do not adhere entirely to scientific standards.